crosspost
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFECREDENTIALS_UNSAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill instructs the agent to access API credentials via environment variables (e.g.,
POSTBRIDGE_API_KEY) to authenticate with external services and describes network operations to send content to remote API endpoints. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied content for adaptation and distribution, which presents a surface where instructions embedded in the data could potentially influence the agent's behavior during the posting process.
- Ingestion points: User-provided source content and platform requirements extracted from the interaction history.
- Boundary markers: None; the skill does not define specific delimiters or instructions to treat user content as data only.
- Capability inventory: Network connectivity via Python's
requestslibrary and integration with several social media platform APIs (X, LinkedIn, Threads, and Bluesky). - Sanitization: No input sanitization, filtering, or validation steps are documented for the content being processed.
Audit Metadata