social-post-writer
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data which could contain malicious instructions designed to override the agent's intended behavior.
- Ingestion points: The skill explicitly requests a 'Topic or idea' and 'Voice/tone' from the user in Step 1, which are then used to generate content in subsequent steps.
- Boundary markers: There are no delimiters (e.g., triple quotes or XML-style tags) or specific instructions provided to the agent to treat the user-supplied topic as data rather than instructions.
- Capability inventory: The skill is primarily focused on text generation and does not utilize tools for network access, file system modification, or command execution.
- Sanitization: The instructions do not include any logic for sanitizing or validating the content of the user-provided inputs before processing.
Audit Metadata