skills/laststance/skills/analyze-app/Gen Agent Trust Hub

analyze-app

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes standard macOS system utilities such as plutil, ls, file, codesign, and strings via a subagent. These commands are used to inspect application metadata, frameworks, and binary types, which is consistent with the skill's stated purpose.
  • [DATA_EXPOSURE]: The skill reads local file metadata and application bundle contents (e.g., Info.plist, framework directories, and resource lists). This access is restricted to the specific application path provided by the user and does not target sensitive user data or system configuration files.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external application bundles, which could theoretically contain adversarial content in metadata fields (like Info.plist). However, the processing is handled through structured analysis steps, and the commands executed are diagnostic in nature, posing a low risk to the agent's integrity.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 03:28 AM
Security Audit — agent-trust-hub — analyze-app