hootsuite-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 processes social media message content retrieved from the Hootsuite API. This data is untrusted and could theoretically contain malicious instructions designed to influence the agent.
- Ingestion points: API calls to
https://platform.hootsuite.com/v1/messagesinSKILL.md. - Boundary markers: None present in the code snippets. No explicit delimiters are used to wrap the message text.
- Capability inventory: Includes network requests via
fetchand console logging. - Sanitization: No content filtering or sanitization is performed on the message text before display beyond simple truncation.
- [SAFE]: The skill correctly manages sensitive information by using
dotenvto load authentication tokens from environment variables rather than hardcoding them.
Audit Metadata