ssrn-econpapers
Pass
Audited by Gen Agent Trust Hub on Apr 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curlto query academic APIs andpython3to parse the resulting data. - [EXTERNAL_DOWNLOADS]: Fetches research paper metadata from well-known academic services including CrossRef, SSRN, RePEc/IDEAS, and Semantic Scholar.
- [REMOTE_CODE_EXECUTION]: Employs a piped execution pattern (
curl | python3) to process API responses. The Python scripts are statically defined within the skill to extract titles, authors, and DOIs from the fetched content. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes untrusted data from external research databases.
- Ingestion points: Research paper metadata is fetched from external APIs in
SKILL.md. - Boundary markers: No specific delimiters or warnings are used to separate fetched content from instructions.
- Capability inventory: The skill has access to
curlandpython3via the platform configuration. - Sanitization: Data is structurally parsed using
json.load()and regular expressions, which limits the data to specific fields like titles and authors.
Audit Metadata