retellai-core-workflow-b
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the retrieval and processing of call transcripts and recording metadata via the
retell.call.retrieveandretell.call.listmethods. Since the content of these transcripts is generated by external callers, it represents a surface where malicious instructions could be embedded to influence the agent's downstream behavior. - Ingestion points:
SKILL.md(Step 3: Get Call Recording and Transcript). - Boundary markers: The instructions do not define clear delimiters or specific instructions for the agent to treat transcript content as untrusted data.
- Capability inventory: The skill is configured to allow
Read,Write,Edit,Bash, andGreptools, providing a significant capability set if an injection were successful. - Sanitization: There is no evidence of transcript sanitization or filtering logic within the provided workflow instructions.
Audit Metadata