ask-me
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interviews the user and records their responses directly into
design/SPEC.md. This creates an attack surface where malicious text provided by a user could be stored and subsequently processed by other agent skills or build tools. - Ingestion points: User responses to the 13-point design tree described in SKILL.md.
- Boundary markers: Absent; the instructions do not specify the use of delimiters or warnings to ignore instructions embedded within user input.
- Capability inventory: The skill is authorized to perform file-write operations to
design/SPEC.md. - Sanitization: Absent; there is no guidance or instruction to sanitize or validate the content of the user's answers before writing them to disk.
Audit Metadata