prioritize
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted external data during its operation, which could contain malicious instructions aimed at overriding agent behavior or biasing prioritization decisions.
- Ingestion points: The skill reads source code, requirements, specifications, and content from remote task trackers as part of its 'Recover the direction' and 'Group outcomes' steps.
- Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions when reading these external files or remote records.
- Capability inventory: The skill is capable of modifying local project documentation (Backlog, Changelog, Working State) and pushing updates to remote task trackers upon authorization.
- Sanitization: The instructions do not define specific sanitization or validation steps for the content ingested from the project environment or remote sources.
Audit Metadata