implement-spec

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data such as specifications, tickets, and research notes to drive its automated implementation workflow.
  • Ingestion points: External data enters the agent context via the issue tracker and the repository's git history (SKILL.md).
  • Boundary markers: The instructions lack explicit requirements for using boundary markers or 'ignore embedded instructions' prompts when passing ticket data to subagents.
  • Capability inventory: The skill manages significant capabilities including creating branches, opening pull requests, and invoking the tdd and code-review tools which involve executing tests and modifying the codebase (SKILL.md).
  • Sanitization: No sanitization or validation mechanisms are described for the content of the tickets or specifications before they are acted upon by the subagents.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 08:23 PM