openrouter-debug-bundle

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_CONTEXT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from an external API (OpenRouter) which could contain malicious instructions if the upstream provider or model is compromised.
  • Ingestion points: In SKILL.md, the debug_request function captures response.choices[0].message.content into a DebugBundle. Similar ingestion occurs in references/examples.md and references/request-logging.md.
  • Boundary markers: The instructions do not define boundary markers or instruct the agent to ignore instructions embedded within the API responses.
  • Capability inventory: The skill has access to Bash (including python3 and node execution) and Write tools, which could be targeted by a successful injection.
  • Sanitization: There is no evidence of sanitization or filtering of the response content before it is stored or displayed.
  • [DYNAMIC_CONTEXT_INJECTION]: The skill uses the dynamic context injection syntax to gather environment information at load time.
  • Evidence: SKILL.md contains !node --version 2>/dev/null || echo 'N/A' and `!`python3 --version 2>/dev/null || echo 'N/A'. These commands are benign as they only report software versions for troubleshooting purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:46 AM
Security Audit — agent-trust-hub — openrouter-debug-bundle