wordpress-router
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from repository configuration files, creating a potential surface for indirect prompt injection.\n
- Ingestion points: The skill reads metadata from
composer.json,package.json,style.css,block.json, andtheme.jsonto classify the project kind (found in SKILL.md and references/decision-tree.md).\n - Boundary markers: No explicit delimiters or instructions to ignore embedded content within these configuration files are provided in the skill instructions.\n
- Capability inventory: The skill environment supports
bashandnode, with capabilities to execute local triage scripts and recommended repository build/test commands.\n - Sanitization: No sanitization or validation of the extracted metadata is mentioned before it is used for workflow routing decisions.\n- [COMMAND_EXECUTION]: The skill executes local scripts and encourages the execution of project-specific tooling.\n
- Evidence: The procedure calls
node skills/wp-project-triage/scripts/detect_wp_project.mjsand suggests running "repo’s lint/test/build commands" based on the triage output recommended by the classification script.
Audit Metadata