extract
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes content from arbitrary external URLs, which constitutes ingestion of untrusted data. This content could contain malicious instructions intended to influence the agent's behavior during subsequent processing steps.\n
- Ingestion points: The
scripts/extract.shscript accepts a list of URLs and retrieves their content via a third-party API.\n - Boundary markers: There are no specific delimiters or instruction-ignore warnings applied to the extracted text before it is returned to the agent.\n
- Capability inventory: The skill performs network requests to an external API and returns the response content to the agent context.\n
- Sanitization: No sanitization or filtering is performed on the extracted content to remove potentially malicious instructions.\n- [EXTERNAL_DOWNLOADS]: The skill makes network requests to
api.inspiro.top. This is the documented and intended behavior of the skill for its primary extraction purpose, using the infrastructure associated with the vendor.
Audit Metadata