skills/datadog-labs/pup/dd-pup/Gen Agent Trust Hub

dd-pup

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the use of the pup CLI tool to interact with Datadog APIs for tasks such as searching logs, querying metrics, and managing monitors.\n- [EXTERNAL_DOWNLOADS]: Installation instructions point to the author's official Homebrew tap (datadog-labs/pack) and GitHub repository to download the required utility.\n- [REMOTE_CODE_EXECUTION]: Includes instructions for building the tool from source using cargo install --git from the vendor's GitHub repository.\n- [PROMPT_INJECTION]: \n
  • Ingestion points: The skill ingests untrusted data from external sources via commands like pup logs search and pup traces search.\n
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious content within the retrieved data.\n
  • Capability inventory: The skill relies on subprocess execution of the pup CLI across all documented modules.\n
  • Sanitization: No sanitization or validation logic is defined for the content fetched from external search results.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 02:09 AM