test-against-spec
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external, potentially untrusted sources including issues, documentation, and live product interfaces. This represents an inherent ingestion surface for indirect prompt injection. However, the skill provides specific instructions to mitigate risk by following explicit sources and stopping for security decisions.
- Ingestion points: Specification sources such as issues, product documentation, and ADRs, as well as live API and UI responses (SKILL.md).
- Boundary markers: The skill instructs the agent to derive behavior only from explicit decisions and to stop for security or material conflicts.
- Capability inventory: Execution of CLI commands, API interactions, and local file modifications during the fixing process.
- Sanitization: The skill does not define specific sanitization routines for data ingested from external sources.
Audit Metadata