cv-content-editor

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill instructions define a legitimate and safe workflow for editing documentation and knowledge base files within a local repository.
  • [COMMAND_EXECUTION]: The skill suggests running npm run validate to verify the integrity of the project's data schemas after edits. This is a standard and safe development command.
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection as it reads and processes local file content from the content/ directory.
  • Ingestion points: Reads markdown and YAML files (e.g., content/knowledge/achievements/, content/case-studies/) during the identification and editing phases.
  • Boundary markers: None identified. The skill reads files directly without specific markers to separate data from instructions.
  • Capability inventory: The skill performs file read/write operations and executes local validation scripts.
  • Sanitization: No sanitization or validation of input file content is mentioned before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 10:47 AM
Security Audit — agent-trust-hub — cv-content-editor