codepulse-exec
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided CodePulse HTML reports as its primary input source without implementing safety boundaries for the untrusted data.
- Ingestion points: The
SKILL.mdfile instructs the agent to read and review an existing CodePulse HTML report provided via a file path. - Boundary markers: The instructions do not define specific delimiters or provide 'ignore embedded instructions' warnings for the agent when parsing the report content.
- Capability inventory: The skill has file-write capabilities, as it is instructed to generate and save summary reports to the
codepulse-exec/reports/directory. - Sanitization: There is no evidence of sanitization, escaping, or filtering of the external report content before it is interpolated into the agent's context.
Audit Metadata