skills/soderlind/skills/wp-bump/Gen Agent Trust Hub

wp-bump

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Uses git, npm, and composer commands to manage the release workflow.
  • [DYNAMIC_EXECUTION]: Extracts script names from package.json and composer.json at runtime and executes them.
  • [EXTERNAL_DOWNLOADS]: May download external packages via npm if project dependencies are missing.
  • [INDIRECT_PROMPT_INJECTION]: Processes untrusted project metadata to drive command execution.
  • Ingestion points: Reads package.json, composer.json, and PHP plugin headers in the repository root (Step 0, SKILL.md).
  • Boundary markers: None present to distinguish data from instructions.
  • Capability inventory: Arbitrary script execution via npm run and composer run (Steps 4 and 5, SKILL.md).
  • Sanitization: No validation of script contents before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 10:21 AM
Security Audit — agent-trust-hub — wp-bump