optise-helix-fitq-audit
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script
scripts/fetch_page.pyto scrape and analyze webpages. - [EXTERNAL_DOWNLOADS]: The
fetch_page.pyscript makes network requests to external URLs provided by the user using Python standard libraries. - [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection. Ingestion points: The skill fetches raw HTML content from arbitrary external URLs via
scripts/fetch_page.py. Boundary markers: No specific delimiters are implemented in the skill instructions to isolate the fetched external content from the agent's logic. Capability inventory: The skill has the capability to execute shell commands and perform network operations. Sanitization: While the script uses regex to extract specific fields, the fetched content is processed by the agent without robust sanitization to prevent malicious instructions embedded in the HTML from being obeyed.
Audit Metadata