datadog-inspector-expert

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a guide for interpreting JSON findings from a security auditing tool. It does not contain executable code, remote downloads, or credential exposure.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from a local cache file located at ~/.cache/claude-grc/findings/datadog-inspector/<run_id>.json. While this presents a surface for indirect prompt injection, the skill's role is primarily interpretive and it lacks the high-privilege capabilities (such as automated script execution or network writing) that would make such an injection high risk.
  • Ingestion points: Processes JSON results from ~/.cache/claude-grc/findings/datadog-inspector/.
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: None; the skill provides guidance for manual review and remediation planning without defining specific tool execution permissions.
  • Sanitization: Not specified in the markdown body.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 12:26 PM
Security Audit — agent-trust-hub — datadog-inspector-expert