bug-triage-pack
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process 'raw reports' from potentially untrusted sources like Slack or customer support tickets. These reports could contain hidden instructions aimed at overriding agent behavior. * Ingestion points: Processes user-provided bug reports and lists of known issues as described in SKILL.md. * Boundary markers: The instructions lack explicit delimiters or warnings for the agent to ignore instructions embedded within the provided data. * Capability inventory: While the skill itself defines no tools, it operates within an environment where the agent may have access to sensitive file system or network capabilities. * Sanitization: There is no requirement for the agent to sanitize or validate the content of the reports before processing.
- [NO_CODE]: The skill contains only markdown instructions and no executable scripts or external code dependencies.
Audit Metadata