jww-issue-reconciliation
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources such as issue descriptions, comments, and pull requests.\n
- Ingestion points: SKILL.md specifies reading relevant issue bodies, replies, and linked pull requests to determine work state.\n
- Boundary markers: There are no explicit instructions for the agent to use delimiters or to ignore potentially malicious instructions within the ingested issue content.\n
- Capability inventory: SKILL.md allows the agent to apply changes to the issue tracker ('apply tracker changes when the request includes them'), creating an automated path influenced by untrusted input.\n
- Sanitization: No sanitization or validation of the input content is mentioned before it is processed or used to perform updates.
Audit Metadata