content-audit

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external content from URLs or local source files (described in 'Step 1: Content Inventory'). This creates a vulnerability to indirect prompt injection, where an attacker could embed malicious instructions in the audited content to influence the agent's behavior.
  • Ingestion points: Website crawling and local file scanning for HTML/text content in SKILL.md.
  • Boundary markers: The instructions do not specify any delimiters or warnings to ignore instructions within the ingested content.
  • Capability inventory: The skill mentions running local scripts (node), generating reports (JSON/Markdown), and routing data to other skills like 'content-improvement-blueprint'.
  • Sanitization: No sanitization or validation steps for the ingested external content are described.
  • [COMMAND_EXECUTION]: The skill documentation instructs the user to execute local shell commands for automation, specifically 'node content-audit/checks.js' and 'npm run report'. These commands run scripts presumably included with the skill to perform the audit and generate reports.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 01:16 PM
Security Audit — agent-trust-hub — content-audit