deadlines

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill's core functionality involves reading and writing to its own application-specific configuration and data files (deadlines.yaml, CLAUDE.md), which is standard behavior for a state-tracking plugin.\n- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for processing untrusted data, though the risk is minimized by the skill's limited capabilities.\n
  • Ingestion points: Data is read from ~/.claude/plugins/config/claude-for-legal/legal-clinic/deadlines.yaml and CLAUDE.md, as well as jurisdiction files in references/plausibility-bands/.\n
  • Boundary markers: Absent; the skill does not explicitly use delimiters to separate record content from instructions.\n
  • Capability inventory: The skill is restricted to file system operations (read and write) on specific paths; it lacks network access, subprocess execution, or arbitrary code execution tools.\n
  • Sanitization: No explicit sanitization or filtering of the file content (e.g., notes or descriptions) is mentioned before it is interpolated into reports.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 03:58 PM
Security Audit — agent-trust-hub — deadlines