Skills
Navigate
skills/warpdotdev/common-skills/write-pr-description/Gen Agent Trust Hub

write-pr-description

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions leverage local command-line tools including git, gh (GitHub CLI), and gcloud to perform read-only operations for fact-gathering. These tools are used to inspect commit logs, diffs, and resource definitions to inform the pull request description.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external git histories and pull request metadata, which introduces a potential surface for indirect prompt injection. This capability is central to the skill's purpose. Evidence chain: 1. Ingestion points: git log, git diff, and gh output. 2. Boundary markers: Absent. 3. Capability inventory: Execution of git, gh, and gcloud. 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 05:28 PM
Security Audit — agent-trust-hub — write-pr-description