skills/promptdriven/pdd/pdd-merge/Gen Agent Trust Hub

pdd-merge

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from several external sources to make decisions about executing shell commands.
  • Ingestion points: Reads project configuration from pdd.json, "owner notes" for operator actions, and external instructions from ../pdd-autopilot/steps/handoff.md.
  • Boundary markers: The skill does not define clear delimiters or specific instructions to ignore embedded commands within the ingested data sources.
  • Capability inventory: The skill has the ability to execute destructive repository actions using gh pr merge and pdd workflow approve.
  • Sanitization: There is no mention of sanitizing or validating the contents of the owner notes or external markdown files before processing them as logic inputs.
  • [COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh) and a vendor-specific tool (pdd) to perform repository operations.
  • Evidence: Uses gh pr merge to modify the repository state and pdd workflow approve to record authorization steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 04:10 PM