implement-spec
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes specifications and tickets, which are external data sources. This creates a surface where instructions embedded in these documents could influence the agent's behavior during implementation. * Ingestion points: SKILL.md (Step 1) reads specs and tickets. * Boundary markers: None explicitly defined to separate data from instructions. * Capability inventory: The skill delegates tasks to other components like /pstack-swarm and /tdd and handles branch merges and PR creation. * Sanitization: Not mentioned.
- [NO_CODE]: This skill contains no executable code or scripts, consisting only of markdown instructions and YAML configuration. This reduces the risk of direct malicious execution or backdoors.
Audit Metadata