Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script
scripts/typefully_scheduler.pyto interact with the Typefully API. This script is included in the skill package and uses only standard libraries. - [EXTERNAL_DOWNLOADS]: The skill communicates with
api.typefully.com, which is a well-known service for social media scheduling. These requests are used to list account details and schedule content. - [CREDENTIALS_UNSAFE]: Sensitive information such as the Typefully API key and Social Set ID are managed through environment variables (
TYPEFULLY_API_KEY,TYPEFULLY_SOCIAL_SET_ID). This is a standard and secure practice for credential management in agent skills. - [DATA_EXFILTRATION]: The skill transmits LinkedIn post content to the Typefully API for scheduling. This data transfer is the core intended functionality of the skill and occurs only after the agent drafts the content based on user input.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the Typefully API (such as lists of scheduled posts) into the agent's context. While this represents a potential ingestion point for untrusted data, the risk is minimal given the specialized nature of the API and the skill's specific use case.
Audit Metadata