task-to-pr

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from tasks, tickets, and pull requests to guide its actions, creating an attack surface for indirect instructions.
  • Ingestion points: Data enters the agent context via task descriptions, tickets, milestones, or pull request content provided in the arguments.
  • Boundary markers: The instructions lack explicit boundary markers or directives to treat ingested task data as untrusted or to ignore embedded instructions.
  • Capability inventory: The skill utilizes tools for code generation, execution of tests via /test, code review via /review, and GitHub operations (commit, push, PR creation, and merging) via the GitHub CLI.
  • Sanitization: There is no evidence of sanitization or filtering of the external task content before it is used to influence code changes or command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 07:10 PM
Security Audit — agent-trust-hub — task-to-pr