implement-spec
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes specifications and tickets from an external issue tracker, creating an attack surface for instructions embedded in data.
- Ingestion points: Data is ingested from a spec, tickets, and research notes as described in
SKILL.md. - Boundary markers: Absent. The instructions do not specify delimiters or warnings for the agent to ignore instructions embedded within the ticket content.
- Capability inventory: As detailed in
SKILL.md, the skill manages git branches and worktrees, spawns subagents for exploration and implementation, and executes tools for testing (tdd) and analysis (code-review). - Sanitization: Absent. There are no instructions to sanitize or validate the content retrieved from the issue tracker before processing.
Audit Metadata