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
WebFetchtool 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, andWebFetch, 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
Bashtool, which is a powerful capability. - Evidence: The skill instructions explicitly direct the agent to run commands like
node .claude/tools/cli/post-analyzer.cjsandnode .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