content-planner

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides the user with an explicit command to execute a local binary: ~/.claude/plugins/cache/nowork-studio/notfair/<version>/bin/notfair-content-calendar. This utility is a vendor-provided tool (from nowork-studio) designed to render the generated JSON data as a visual calendar in a web browser.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from the Google Search Console (GSC) API and interpolates it into prompts for downstream agents.
  • Ingestion points: Step 2 fetches query and page data directly from the GSC API.
  • Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands when processing GSC query strings.
  • Capability inventory: The skill writes to the local file system (content-calendar.json) and generates a writerPrompt field intended to control the behavior of the /content-writer skill.
  • Sanitization: While the skill enforces quality checks like 'hook-driven titles', it does not describe mechanisms to sanitize or escape potential prompt injection strings found within GSC query data.
  • [DATA_EXPOSURE]: The skill reads from and writes to the ~/.notfair/ directory, including caching sensitive search performance data in gsc-cache.json. This behavior is consistent with the skill's stated purpose of SEO analysis and roadmap generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 03:14 PM
Security Audit — agent-trust-hub — content-planner