doi-content-negotiation
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The SKILL.md file provides several curl command examples for retrieving metadata from the official doi.org resolver using various Accept headers for different formats. These commands are standard for research workflows and target a well-known service.\n- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it retrieves and processes bibliographic content from external research publishers.\n
- Ingestion points: Metadata fields such as titles, authors, and abstracts are fetched from the https://doi.org/ resolver as demonstrated in the Python and curl usage examples in SKILL.md.\n
- Boundary markers: The skill does not implement delimiters or specific instructions to the agent to ignore potential commands within the fetched metadata.\n
- Capability inventory: The Python code in SKILL.md demonstrates network access (GET requests) and the ability to write files to the local system (references.bib).\n
- Sanitization: No sanitization or validation is performed on the data received from the external DOI API before it is printed to the console or saved to a file.
Audit Metadata