Skills
Navigate
skills/richfrem/agent-plugins-skills/compile-apm-package/Gen Agent Trust Hub

compile-apm-package

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill workflow involves running python scripts/validate_apm_package.py and apm compile using the Bash tool. These commands are necessary for package validation and compilation but involve shell interaction. The validation script validate_apm_package.py is not provided in the skill package for inspection.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by merging content from the .apm/context/ directory into primary instructions like AGENTS.md or GEMINI.md. 1. Ingestion points: File data from the .apm/context/ directory enters the context. 2. Boundary markers: No delimiters or protective instructions are specified to segregate merged fragments. 3. Capability inventory: Access to Bash, Read, and Glob tools enables file and command operations. 4. Sanitization: No sanitization of the merged content is documented.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 08:07 PM
Security Audit — agent-trust-hub — compile-apm-package