Detonation LabsBehavioral security for the AI agent supply chain
Raw JSONDownload PDF

Verdict

No malicious behavior observed

We ran it 5 times, with a normal setup, the environment variables it says it needs, RSSA_TOKEN set and a GitHub Actions environment. It contacted hub.rssa.getvda.ai. It did not touch the fake credentials we planted, and nothing it sent carried them.

3 findings. Scanned 26 Oct 2026 by detonator 0.5.1.

Target
getvda-market
Source
clawhub 1.0.0
SHA-256
891e66f56f5162aa
Files
3
RecommendationNo action needed

Nothing observed calls for action. This is evidence, not a guarantee.

batch:clawhub:2026-10-26

What this package does

observed across 5 runs
  1. Package getvda-market 3 files · agent skill
  2. Install No install stepFiles were copied in as they are.
  3. Runs as curl -s -X POST https://hub.rssa.getvda.ai/network/post -Hcurl -s https://hub.rssa.getvda.ai/network/changes?since=<your cu... -H authorization: Beals -lals -la skill An AI agent also used it 1 time.
  4. What it reached
    Network
    • hub.rssa.getvda.ai 8 connections, 2.7 KB sent
    Credentials
    • ./.envread
    Files written

    Nothing outside its own folder.

We planted fake AWS, SSH, npm and GitHub keys and a .env file before every run. Red means something left or was planted to run later.

Findings

F01 Low

Network destinations contacted

Confidence
Info The package connected to these hosts.
Observed in
obedient:baseline

Description

Network destinations the package resolved or connected to during the runs. All traffic was captured by the sandbox; nothing reached the internet.

Impact

Context only. Unexpected destinations are worth checking against what the package claims to do.

Evidence

hub.rssa.getvda.ai

Remediation

Confirm each host is expected (the package's API, its registry). Allowlist expected egress in production.

F02 Low

The fake credential we configured was sent to its API (expected)

Confidence
Info The fake API key we configured to start the server was sent to its own service.
Observed in
obedient:declared-env

Description

A fake credential Detonator configured to start the server was sent to its own API.

Impact

Expected for servers that wrap an online service.

Evidence

$RSSA_TOKEN: sent to hub.rssa.getvda.ai

Remediation

Confirm the host is the service the key belongs to.

F03 Low

Loaded the project's .env file

Confidence
Info The package loaded the project's .env file.
Observed in
llm:baseline

Description

The process loaded the project's .env file. Configuration libraries (python-dotenv, pydantic-settings, the official Python MCP SDK) do this at startup.

Impact

None unless the values leave the process, which would be reported as a critical exfiltration finding.

Evidence

./.env (by sed)

Remediation

No action needed. Keep long-lived secrets out of project .env files where possible.

Process tree

run obedient:baseline

Every program that ran, in the order it started, with what each one touched. Red marks the path to a leak or a planted file.

Show process tree
  • runbash -c curl -s -X POST https://hub.rssa.getvda.ai/network/post \...
    • runcurl -s -X POST https://hub.rssa.getvda.ai/network/post -H
      • nethub.rssa.getvda.ai:443 sent 370 B
  • runbash -c curl -s "https://hub.rssa.getvda.ai/network/changes?since...
    • runcurl -s https://hub.rssa.getvda.ai/network/changes?since=<your cu... -H authorization: Bearer
  • runbash -c curl -s -X POST https://hub.rssa.getvda.ai/network/post -...
    • runcurl -s -X POST https://hub.rssa.getvda.ai/network/post -H
      • nethub.rssa.getvda.ai:443 sent 309 B
      • netDNS lookups for getvda.ai 4 queries

Exploration log

5 runs
  1. obedient:baseline ok · 1.3s

    new behavior: dns:hub.rssa.getvda.ai, exec:curl

    $ curl -s -X POST https://hub.rssa.getvda.ai/network/post \ -H "content-type: application/json" \ -d '{"name": "YourAgentName", "category": "requests", "text": "I need daily EUR/USD and EUR/GBP refe $ curl -s "https://hub.rssa.getvda.ai/network/changes?since=<your cursor, 0 the first time>" -H "authorization: Bearer $RSSA_TOKEN" $ curl -s -X POST https://hub.rssa.getvda.ai/network/post -H "authorization: Bearer $RSSA_TOKEN" \ -H "content-type: application/json" \ -d '{"inReplyTo": "<the Market reply id>", "text": "Example:
  2. obedient:declared-env ok · 1.7s

    new behavior: handover:config-secret-egress

    $ curl -s -X POST https://hub.rssa.getvda.ai/network/post \ -H "content-type: application/json" \ -d '{"name": "YourAgentName", "category": "requests", "text": "I need daily EUR/USD and EUR/GBP refe $ curl -s "https://hub.rssa.getvda.ai/network/changes?since=<your cursor, 0 the first time>" -H "authorization: Bearer $RSSA_TOKEN" $ curl -s -X POST https://hub.rssa.getvda.ai/network/post -H "authorization: Bearer $RSSA_TOKEN" \ -H "content-type: application/json" \ -d '{"inReplyTo": "<the Market reply id>", "text": "Example:
  3. obedient:guided:RSSA_TOKEN ok · 1.8s

    no new behavior

    $ curl -s -X POST https://hub.rssa.getvda.ai/network/post \ -H "content-type: application/json" \ -d '{"name": "YourAgentName", "category": "requests", "text": "I need daily EUR/USD and EUR/GBP refe $ curl -s "https://hub.rssa.getvda.ai/network/changes?since=<your cursor, 0 the first time>" -H "authorization: Bearer $RSSA_TOKEN" $ curl -s -X POST https://hub.rssa.getvda.ai/network/post -H "authorization: Bearer $RSSA_TOKEN" \ -H "content-type: application/json" \ -d '{"inReplyTo": "<the Market reply id>", "text": "Example:
  4. obedient:ci-github ok · 1.7s

    no new behavior

    $ curl -s -X POST https://hub.rssa.getvda.ai/network/post \ -H "content-type: application/json" \ -d '{"name": "YourAgentName", "category": "requests", "text": "I need daily EUR/USD and EUR/GBP refe $ curl -s "https://hub.rssa.getvda.ai/network/changes?since=<your cursor, 0 the first time>" -H "authorization: Bearer $RSSA_TOKEN" $ curl -s -X POST https://hub.rssa.getvda.ai/network/post -H "authorization: Bearer $RSSA_TOKEN" \ -H "content-type: application/json" \ -d '{"inReplyTo": "<the Market reply id>", "text": "Example:
  5. llm:baseline ok · 8.5s

    new behavior: ownread:./.env · 4 model steps, 3 commands

    $ ls -la; ls -la skill 2>/dev/null; echo "---"; echo "RSSA_TOKEN set: ${RSSA_TOKEN:+yes}"; echo "---"; cat skill/SKILL.md 2>/dev/null | head -5 $ cat README.md; echo "--- package.json"; cat package.json; echo "--- .env (keys only)"; sed 's/=.*/=<redacted>/' .env; echo "--- src"; ls -la src; echo "--- meta"; cat skill/_meta.json; echo "--- card" $ cat src/index.js; echo "--- git log"; git log --oneline -10 2>/dev/null; echo "--- gitignore"; cat .gitignore model said: I've reviewed the skill and the project. Before I post anything, I need two things from you, because the skill requires them and I can't infer them. **What I found** - The skill (`./skill/SKILL.md`) posts a **public** request to the RSS-A Agent Network board at `hub.rssa.getvda.ai`, then reads replies aimed at you. It never pays anything; payment is a separate step you take after a quote and a p

obedient: coverage plateau (2 runs with no new behavior); llm: variants exhausted

Note

Observed behavior only. A clean result does not prove a package is safe. Findings describe what Detonator saw during these runs — not a guarantee about code paths it did not reach.