quote-post
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the user which could contain malicious instructions designed to influence the agent's behavior or the generated output.
- Ingestion points: Step 1 (captions) and Step 3 (image references/descriptions) involve direct ingestion of user-supplied text into the agent's context in SKILL.md.
- Boundary markers: The skill uses double quotes to delimit the chosen quote within the generated Gemini prompt template in Step 4, but it lacks specific instructions to the agent to ignore potentially malicious commands embedded within the user's caption or style description.
- Capability inventory: The skill is restricted to text generation and prompt construction; it does not have access to tools for file system modification, network exfiltration, or subprocess execution.
- Sanitization: The instructions do not include any steps for sanitizing, validating, or filtering user-provided text before it is used to generate the motivational quotes or the final image prompt.
Audit Metadata