skills/mcouthon/agents/deep-research/Gen Agent Trust Hub

deep-research

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a structured methodology for research and documentation. No malicious patterns such as command execution, data exfiltration, or persistence were found.
  • [PROMPT_INJECTION]: The skill processes untrusted data from the web (WebFetch, WebSearch) and has filesystem access (Read, Grep, Glob, LSP), which constitutes an indirect prompt injection attack surface. 1. Ingestion points: WebFetch and WebSearch tools in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Read, Grep, Glob, and LSP tools in SKILL.md. 4. Sanitization: Absent. As the skill's primary purpose is read-only research, the risk is negligible and consistent with intended functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 05:07 AM