qa-session

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the 'gh' CLI tool via Bash to create GitHub issues, which is consistent with its stated purpose of managing bug reports.
  • [PROMPT_INJECTION]: There is a potential indirect prompt injection surface when the agent processes untrusted data.
  • Ingestion points: User-provided bug reports via arguments and the local 'UBIQUITOUS_LANGUAGE.md' file are ingested into the agent's context in SKILL.md.
  • Boundary markers: The instructions do not provide explicit delimiters or instructions to ignore potential commands embedded in the bug reports or documentation.
  • Capability inventory: The skill has access to the 'Bash' and 'Agent' tools, allowing it to execute system commands and perform autonomous exploration in SKILL.md.
  • Sanitization: No validation, escaping, or filtering of the external content is implemented before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 12:05 AM
Security Audit — agent-trust-hub — qa-session