open-knowledge-pack-knowledge-base-consolidate

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the exec() function to perform local file system operations, such as searching for keywords, listing directory contents, and reading file data.
  • Evidence: Employs grep -rn <topic-keyword> <content-dir> to locate research documents, ls -A research to list files, and cat <path> to retrieve file contents.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to ingest and synthesize content from research articles and external sources which may contain untrusted data.
  • Ingestion points: The skill reads research articles and their referenced sources via exec("cat <path>") in Step 1 of the consolidation process.
  • Boundary markers: No specific delimiters or warnings to ignore embedded instructions are implemented when reading external source files.
  • Capability inventory: The skill has access to exec (shell commands), cat, grep, and edit (file writing) tools.
  • Sanitization: No sanitization or validation of the ingested markdown content is described before it is synthesized into the final canonical article.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 02:16 AM
Security Audit — agent-trust-hub — open-knowledge-pack-knowledge-base-consolidate