internal-linking-optimizer

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell pipes to execute internal Python components: python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/crawl.py" and python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/linkgraph.py". These scripts are used to calculate technical SEO metrics like click-depth and internal PageRank from site data.
  • [EXTERNAL_DOWNLOADS]: As part of its primary SEO function, the skill crawls external websites and sitemaps provided by the user to analyze link structures and identify orphan pages.
  • [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it processes content from external, potentially untrusted web pages during the crawling process.
  • Ingestion points: Data enters the system via the crawl.py script which fetches content from user-provided URLs.
  • Boundary markers: The instructions do not define specific delimiters or "ignore previous instructions" warnings when processing the crawled web content.
  • Capability inventory: The skill has the capability to write files to the memory/audits/ directory to store reports.
  • Sanitization: There is no mention of sanitization, validation, or escaping of the content retrieved from external URLs before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 03:30 PM
Security Audit — agent-trust-hub — internal-linking-optimizer