to-issues-yes
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes potentially untrusted data from an external source.
- Ingestion points: The agent fetches and reads full bodies and comments from a remote issue tracker (SKILL.md).
- Boundary markers: There are no explicit instructions for the agent to use delimiters or to ignore potentially malicious embedded commands within the fetched issue data.
- Capability inventory: The agent has the capability to explore the local codebase (Step 2) and publish new issues to a remote issue tracker (Step 5).
- Sanitization: No data validation or sanitization steps are defined for the content retrieved from the external issue tracker before it is used to draft and publish new issues.
Audit Metadata