backlinks-list
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: Executes a localized bash script (
scripts/get_backlinks_list.sh) to perform network operations and data processing. - [EXTERNAL_DOWNLOADS]: Fetches data from the Frevana API service at
https://ai-factory.frevana.com. This is the primary function of the skill. - [DATA_EXFILTRATION]: Sends a user-provided API token and query parameters to the Frevana API. The script follows security best practices by preventing the token from being printed to the console.
- [PROMPT_INJECTION]: The skill ingests data from an external API and presents it to the agent, creating a potential surface for indirect prompt injection.
- Ingestion points: Data is received from
ai-factory.frevana.comwithin thescripts/get_backlinks_list.shscript. - Boundary markers: The output is returned as raw JSON to the agent's context without explicit boundary delimiters.
- Capability inventory: The skill has access to shell and Python execution environments.
- Sanitization: The script validates that the API response is valid JSON format before returning it.
Audit Metadata