issue-implementation
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and act upon external, untrusted content from issue trackers, PRDs, and existing codebases.
- Ingestion points: The 'Intake' phase in
SKILL.mdexplicitly requires fetching and reading issues and acceptance criteria from external documents (PRDs). - Boundary markers: The instructions do not define clear delimiters or use 'ignore-embedded-instructions' patterns when processing the fetched issue content.
- Capability inventory: The orchestrator has the capability to dispatch subagents, execute version control (VCS) commands, commit code, and push to remote repositories.
- Sanitization: There is no explicit sanitization or validation of the input data before it is passed to the planning or implementation subagents.
Audit Metadata