cat-run-and-read-results
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides numerous examples for executing the
catclitool, which is a vendor-owned resource for the author 'justcatit'. It demonstrates standard usage of command-line flags for test filtering (-f,-i,-e), logging (-l), and ad-hoc runs (-n). - [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow where the agent ingests and interprets test results generated by
catclior provided in output files. This creates an attack surface for indirect prompt injection if the test data contains malicious instructions. - Ingestion points: Console output from
catcliand project output files (e.g., JUnit, TRX, or JSON formats). - Boundary markers: None identified in the provided instructions; the agent is simply told to read the console or output files.
- Capability inventory: The skill primarily uses shell command execution via the
catclitool. - Sanitization: None described; the agent is expected to parse failure messages and queries directly from the tool's output.
Audit Metadata