test-stinky
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze arbitrary test files, CI configurations, and runner settings from the user's repository to detect quality smells.
- Ingestion points: Audit targets include all test files, runner configurations, and CI step definitions across the entire repository (as defined in SKILL.md and references/suite-pass.md).
- Boundary markers: Absent. The instructions do not provide delimiters or "ignore instructions" warnings to help the agent distinguish between code-under-test and potentially malicious embedded prompts.
- Capability inventory: The skill itself declares no execution capabilities (permissions.yaml), but the agent using the skill typically possesses capabilities for file system operations and shell execution to implement the proposed quality fixes.
- Sanitization: No sanitization, filtering, or validation of the processed content is specified or performed.
Audit Metadata