dd-audit-compliance-report

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the pup command-line utility and jq to query and process audit logs. This is standard behavior for the tool's intended use case as a Datadog reporting assistant and originates from a trusted vendor.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes audit log data that could potentially contain untrusted strings. While this is a theoretical attack surface, the risk is minimized by structural extraction of specific JSON keys.
  • Ingestion points: Audit log data enters via the output of pup audit-logs search as seen in SKILL.md.
  • Boundary markers: The report template in SKILL.md does not use explicit delimiters to isolate external log data from the agent's instructions.
  • Capability inventory: The skill uses subprocesses to execute pup and jq for data retrieval and manipulation.
  • Sanitization: Content is filtered through jq to select specific attributes, providing structural control over the ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 03:34 PM
Security Audit — agent-trust-hub — dd-audit-compliance-report