oma-scholar

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The file resources/upstream-spec-cache.md contains directive language ([CLAUDE MUST DO]) written in Chinese, instructing the agent to proactively inform the user about API key configuration every time the skill is activated. While the file includes a disclaimer stating it is third-party reference material, the presence of imperative commands targeting agent behavior is a detected pattern.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from research papers (PDF, LaTeX, abstracts) to extract structured information. This creates a surface where malicious instructions embedded in paper text could attempt to influence the agent's output or actions during the sidecar generation process.
  • Ingestion points: The skill ingests untrusted text from PDF files, LaTeX sources, and research abstracts.
  • Boundary markers: While the skill enforces a strict YAML schema, it lacks specific boundary markers (e.g., delimiters) to separate processed untrusted text from internal instructions.
  • Capability inventory: The skill has the capability to write local YAML files, perform network requests to academic APIs, and execute bundled Python scripts.
  • Sanitization: The skill includes a scripts/sanitize.py utility intended to clean structural corruption in generated YAML, though its primary focus is on formatting rather than security sanitization of input content.
  • [EXTERNAL_DOWNLOADS]: The skill performs network operations to fetch scholarly data from knows.academy, api.openalex.org, and semanticscholar.org. These are well-known academic services and are documented as the intended data sources for the skill's research functions.
  • [DYNAMIC_EXECUTION]: The skill executes bundled Python scripts, including gen.py, lint.py, sanitize.py, and verify_metadata.py, to handle YAML generation, validation, and metadata verification. These scripts are run locally via python3 as part of the skill's core functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 04:52 PM