citeclaw-bibliography-curation

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to execute shell commands such as npx citeclaw for bibliography management, latexmk for compiling documents, and rg for searching logs.
  • [EXTERNAL_DOWNLOADS]: Fetches and runs the citeclaw utility from the npm registry using npx to perform citations and metadata resolution.
  • [PROMPT_INJECTION]: The skill processes untrusted external data from sources like arXiv, GitHub repository lists, and web search results, which creates a surface for indirect prompt injection.
  • Ingestion points: Scraped content from arXiv URLs, third-party GitHub curated lists, and general search engine results.
  • Boundary markers: None; the instructions do not specify the use of delimiters or instructions for the agent to ignore instructions embedded in the external metadata.
  • Capability inventory: Shell command execution for running npx, latexmk, and rg on the host system.
  • Sanitization: The workflow does not include explicit validation or sanitization steps for the metadata retrieved from external sources before it is processed or written to files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 04:46 PM
Security Audit — agent-trust-hub — citeclaw-bibliography-curation