skills/daxaur/openpaw/c-apps/Gen Agent Trust Hub

c-apps

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes mas CLI commands to perform searches, installations, and updates for Mac App Store applications.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from Mac App Store search results without sanitization.\n
  • Ingestion points: Output from the mas search command (SKILL.md).\n
  • Boundary markers: Absent; there are no delimiters or instructions to ignore embedded commands in search results.\n
  • Capability inventory: The skill has the ability to install and upgrade software (mas install, mas upgrade) based on IDs found during search (SKILL.md).\n
  • Sanitization: No sanitization or validation of external content returned by the App Store is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 08:44 AM
Security Audit — agent-trust-hub — c-apps