doc-ears-autopilot

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were detected. The skill implements a legitimate automated documentation workflow within the specified project environment.- [COMMAND_EXECUTION]: The skill utilizes local shell commands (e.g., 'ls', 'grep', 'sort', 'tail') and executes local scripts (e.g., 'validate_ears.py', 'pre_ears_generation.sh') for file discovery and validation. These operations are restricted to the local workspace and do not involve remote execution of untrusted code.- [PROMPT_INJECTION]: The skill body consists of functional instructions and workflow definitions. It does not contain bypass markers, role-play injections, or instructions to ignore safety filters.- [DATA_EXFILTRATION]: File access is limited to internal documentation paths (docs/02_PRD, docs/03_EARS). There are no network calls to external or non-whitelisted domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 10:25 PM