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