skills/affaan-m/ecc/agent-sort/Gen Agent Trust Hub

agent-sort

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted repository data to determine project dependencies and configuration.
  • Ingestion points: Processes project configuration files (such as package.json, pyproject.toml, Cargo.toml) and source files via rg and cat commands during repository analysis.
  • Boundary markers: Absent. The instructions do not specify any delimiters or instructions for the agent to ignore potential malicious prompts embedded within project files.
  • Capability inventory: Performs file reading (cat, rg) and file writing (creates an optional library router file at .claude/skills/skill-library/SKILL.md).
  • Sanitization: Absent. No validation or escaping of the ingested text is described before it is used to generate the install plan or router skill content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 11:07 PM
Security Audit — agent-trust-hub — agent-sort