dd-pup

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the pup CLI and jq to perform administrative tasks and data processing. These commands are within the expected scope for managing Datadog resources via a command-line interface.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from Datadog API outputs (logs, metrics, traces, events) and local JSON files, which represents a potential surface for indirect prompt injection if those sources contain adversarial content.
  • Ingestion points: Data is ingested via pup commands that search logs, list monitors, and fetch resource details throughout SKILL.md.
  • Boundary markers: No specific boundary markers or 'ignore embedded instructions' warnings are provided in the prompt templates.
  • Capability inventory: The skill has the capability to execute shell commands (pup, jq), perform file system operations (read/write via redirection and --file flags), and make network requests to Datadog APIs.
  • Sanitization: There is no explicit sanitization or validation of the data retrieved from Datadog APIs before it is incorporated into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:06 AM
Security Audit — agent-trust-hub — dd-pup