status

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands including wc, ls, grep, and sed to calculate line counts and list files within the project's memory directories.
  • [PROMPT_INJECTION]: The skill processes the content of MEMORY.md to identify and verify file references. Ingestion points: Reads the contents of MEMORY.md (Step 3) to find file paths. Boundary markers: No delimiters or ignore-instructions markers are present. Capability inventory: Limited to local file read and metadata operations (wc, ls, grep). Sanitization: The skill uses a regular expression ([a-zA-Z0-9_/.-]+\.(ts|js|py|md|json|yaml|yml)) to strictly extract only potential filenames, preventing the execution of arbitrary embedded instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 01:23 PM