intentline-issue
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process external data from issue trackers. It includes specific defensive instructions to treat all retrieved text as untrusted data and to ignore any instructions embedded within that data that attempt to bypass safety guidelines or widen the agent's scope.
- [EXTERNAL_DOWNLOADS]: The skill references documentation and examples hosted on GitHub within the 'grove/intentline' repository. These resources belong to the skill's author and are used for instructional purposes.
- [SAFE]: The skill emphasizes the use of host-provided tools and authenticated operations, explicitly directing the agent not to request tokens, install unauthorized SDKs, or execute unapproved scripts.
Audit Metadata