to-spec
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from the conversation history and the codebase to generate specifications that are published to a project issue tracker. This creates an attack surface where malicious instructions embedded in the source data could influence the agent's synthesized output or the publishing process.
- Ingestion points: Current conversation context and codebase understanding as specified in SKILL.md.
- Boundary markers: Absent; the instructions do not define specific delimiters or headers to isolate untrusted content from the agent's operational logic.
- Capability inventory: The skill has the capability to publish synthesized content to an external project issue tracker.
- Sanitization: The skill does not provide instructions for escaping, filtering, or validating the ingested content before it is processed and published.
Audit Metadata