postwire
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to generate social media captions, which constitutes a potential surface for indirect prompt injection where malicious instructions could be embedded in the input data.
- Ingestion points: The
promptfield in the/api/generateendpoint (SKILL.md). - Boundary markers: The skill includes a 'Confirm Before Publishing' section that explicitly instructs the agent to show the exact text to the user and wait for a 'yes' before posting.
- Capability inventory: The skill uses
curlto make network requests to thepostwire.ioAPI for content publishing and scheduling. - Sanitization: The skill relies on mandatory manual user review and confirmation as the primary mitigation against unintended or malicious output generation.
- [COMMAND_EXECUTION]: The skill documentation provides
curlcommand examples for interacting with the PostWire API. These are standard API usage instructions and do not involve unsafe interpolation or arbitrary command execution. - [DATA_EXFILTRATION]: The skill performs network operations to the vendor's domain (
postwire.io). This is the intended primary purpose of the skill and does not involve exfiltration of sensitive local data.
Audit Metadata