backlinks-index
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a bundled shell script (
get_backlinks_index.sh) which serves as a wrapper for API interactions. - [COMMAND_EXECUTION]: The shell script utilizes inline Python code via heredocs to perform robust JSON parsing, input validation, and result processing.
- [EXTERNAL_DOWNLOADS]: The skill performs network requests to
ai-factory.frevana.comusingcurlto retrieve backlink index data. - [PROMPT_INJECTION]: The skill ingests external data from the Frevana API into the agent context, creating an indirect prompt injection surface. The risk is mitigated by explicit JSON validation of the response.
- Ingestion points: API response fetched via
curlfromai-factory.frevana.cominscripts/get_backlinks_index.sh. - Boundary markers: None present in the skill instructions.
- Capability inventory: Subprocess execution (curl, python3), file system write access to the
./out/directory. - Sanitization: Employs
json.loads()within a Python script to verify the integrity and format of the response data before it is returned to the agent.
Audit Metadata