Skills
skills/laurigates/claude-plugins/project-distill/Gen Agent Trust Hub

project-distill

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs shell discovery at load time using the dynamic context injection syntax. Evidence: !find commands in SKILL.md identify project structure. These are local, non-interactive discovery operations.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests and processes historical conversation data and project files. Ingestion points: SKILL.md (via conversation history review), project rules, and skill files. Boundary markers: Absent. Capability inventory: Write and Edit tools, git and just commands. Sanitization: Absent. The risk is mitigated by a required user confirmation step (AskUserQuestion) before any modifications are applied.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 01:18 AM