compile-apm-package

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes 'python scripts/validate_apm_package.py' and 'apm compile' to process package primitives. These are standard local operations for a build tool authored by richfrem.
  • [PROMPT_INJECTION]: The skill processes APM primitives to generate merged context documents, creating a surface for indirect prompt injection. Ingestion points: APM primitives and source files within the .apm/ directory. Boundary markers: None explicitly specified in the prompt instructions, but a validation step is included. Capability inventory: Uses Bash for script execution and Read/Glob for file system access. Sanitization: Uses scripts/validate_apm_package.py to verify package integrity before compilation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 12:57 PM
Security Audit — agent-trust-hub — compile-apm-package