content-analyzer

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted text from external URLs and files which can contain instructions designed to bypass agent guidelines or influence behavior.
  • Ingestion points: External data is fetched via the 'url' parameter using the WebFetch tool or read from external files (SKILL.md, schemas/input.schema.json).
  • Boundary markers: There are no delimiters or specific instructions for the agent to ignore or isolate instructions found within the content being analyzed.
  • Capability inventory: The agent has access to Bash, Write, and WebFetch, which could be abused if the agent obeys malicious instructions in the analyzed data.
  • Sanitization: No methods for sanitizing or filtering ingested web content are defined.
  • [COMMAND_EXECUTION]: The skill's workflow depends on executing local JavaScript files via the Bash tool, which is a powerful capability.
  • Evidence: The skill instructions explicitly direct the agent to run commands like node .claude/tools/cli/post-analyzer.cjs and node .claude/lib/memory/memory-search.cjs (SKILL.md).
  • Context: These scripts are vendor-controlled resources intended for CLI integration, but they are not included in the provided file set for verification.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 10:04 AM