vibe-to-spec
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted voice transcripts that could potentially contain malicious instructions intended to influence the agent's behavior during the specification generation process.
- Ingestion points: The skill reads a "voice dump" provided by the user as the primary input for normalization and specification generation (defined in
SKILL.md). - Boundary markers: The instructions do not specify any delimiters or boundary markers to distinguish between legitimate user data and potential embedded instructions within the voice transcript.
- Capability inventory: The skill is capable of generating and writing a
SPEC.mdfile and other implementation pack components based on the processed input (defined inSKILL.md). - Sanitization: There is no explicit requirement for the agent to sanitize, escape, or filter the content of the voice dump before incorporating it into the final output.
Audit Metadata