crossref-search
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to run the call.mjs script to perform searches and handle payments.
- [EXTERNAL_DOWNLOADS]: The documentation instructs the user to download the client script from https://fittings.sh/skill/call.mjs if not already present.
- [REMOTE_CODE_EXECUTION]: The script call.mjs implements an integrity check that fetches a hash from https://fittings.sh/skill/call.mjs.sha256 and prompts the user to re-download the script from the remote server if the local version is out of date, establishing a remote update dependency.
- [PROMPT_INJECTION]: The skill processes external search results from the Crossref API via a proxy, which is a potential surface for indirect prompt injection.
- Ingestion points: Bibliographic metadata from fittings.sh is printed to the console.
- Boundary markers: None identified in the provided scripts.
- Capability inventory: The script can execute network requests and signs authorizations using a private key.
- Sanitization: No sanitization is performed on the data retrieved from the remote API before output.
Audit Metadata