open-knowledge-pack-knowledge-base-research

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the exec tool to run shell commands like grep, ls, and cat for scanning the local content directory to identify and read existing research documents.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to use WebFetch and WebSearch capabilities to retrieve information from external URLs, research papers, and public repositories to gather evidence for articles.
  • [INDIRECT_PROMPT_INJECTION]: The research process involves ingesting and analyzing untrusted content from third-party websites and external sources.
  • Ingestion points: External data enters the context via WebFetch and WebSearch tools during the source capture phase.
  • Boundary markers: The skill relies on platform-level grounding and linking rules mentioned in the open-knowledge base skill, though specific delimiters for external content are not defined in this instruction set.
  • Capability inventory: The skill can execute shell commands (exec), write to the filesystem (edit), and perform network requests (WebFetch).
  • Sanitization: No explicit sanitization or filtering of external content is described in this specific skill file.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 02:16 AM
Security Audit — agent-trust-hub — open-knowledge-pack-knowledge-base-research