bug-interview
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- PROMPT_INJECTION (LOW): The skill possesses an indirect prompt injection surface related to its bug report processing logic.
- Ingestion points: User bug descriptions and the 'bug-name' placeholder used in file paths (SKILL.md).
- Boundary markers: Absent; user-provided data is directly interpolated into the markdown plan template without delimiters or instructions to ignore embedded commands.
- Capability inventory: The skill writes markdown files to the '.claude/plans/' directory, which involves file-system access; there is a minor risk of path traversal if the 'bug-name' is manipulated.
- Sanitization: Absent; no validation or escaping of user-provided content or filenames is specified in the skill's logic.
Audit Metadata