cli-output-review
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues were detected. The skill's operations are limited to reading local repository files for analysis. No external network connections, sensitive file access, or command execution patterns were found.
- [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by reading files from the repository. This is evaluated as safe because the agent is not granted any capabilities to execute commands or exfiltrate data.
- Ingestion points:
crates/cli/output snapshots and files in.agents/agents/and.agents/rules/. - Boundary markers: None identified.
- Capability inventory: Analysis only; no subprocess, network, or file-write operations detected.
- Sanitization: Not performed on ingested content.
Audit Metadata