qa
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill uses the
ghtool to transmit data to GitHub by creating issues. This data includes user-provided bug descriptions and context gathered from exploring the local codebase. This behavior is consistent with the skill's stated purpose of filing issues to a well-known service.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by processing untrusted user input and incorporating it into GitHub issue bodies.\n - Ingestion points: User descriptions of bugs and expected behaviors (SKILL.md).\n
- Boundary markers: The skill does not define explicit delimiters or warnings to ignore instructions embedded within the user's bug reports.\n
- Capability inventory: Employs
gh issue createfor external reporting and a subagent for local codebase exploration (SKILL.md).\n - Sanitization: There is no mention of sanitizing, escaping, or validating user input before it is used to populate GitHub issue templates.
Audit Metadata