dd-audit-compliance-report
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
pupCLI andjqto fetch and process audit log data. These commands are necessary for the skill's primary function of generating audit reports.\n- [PROMPT_INJECTION]: The skill processes log data from the Datadog API, which may contain attacker-influenced strings. This represents a potential surface for indirect prompt injection if malicious instructions were embedded in log fields.\n - Ingestion points: JSON output from
pup audit-logs searchcommands inSKILL.md.\n - Boundary markers: Data is interpolated directly into the evidence report template without specific delimiters.\n
- Capability inventory: Formatting text and populating markdown tables.\n
- Sanitization: Not explicitly performed; relies on standard agent behavior for handling external text.
Audit Metadata