sm-post
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXFILTRATION]: The skill transmits user-confirmed content to the Ayrshare API (api.ayrshare.com) to perform its primary function of social media posting. This is a legitimate use of a well-known service.
- [COMMAND_EXECUTION]: The skill uses a bash helper script (post.sh) to invoke curl and jq. Arguments are passed safely to jq using the --arg flag to prevent JSON injection, and the script includes validation for the required environment variables.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface through the --file argument which reads local file content. However, the risk is mitigated by explicit instructions in SKILL.md requiring the agent to finalize content and obtain manual user confirmation before the API call is executed.
- [CREDENTIALS_UNSAFE]: Secrets are managed via the AYRSHARE_API_KEY environment variable. The skill correctly instructs users to manage this key in their environment or .env files (which are ignored by git), and the script verifies its presence before execution without logging the key.
Audit Metadata