x-posting
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface identified due to interaction with untrusted external content.\n
- Ingestion points: The skill instructions in SKILL.md direct the agent to check and read notifications and engagement from X (Twitter) at the start of every session.\n
- Boundary markers: The skill lacks explicit boundary markers or instructions to isolate external data from the agent's internal logic.\n
- Capability inventory: The instructions in SKILL.md grant the agent capabilities to navigate to arbitrary product URLs, capture screenshots, and publish posts and replies publicly.\n
- Sanitization: No sanitization, validation, or filtering processes are specified for the external text retrieved from X before it is used to influence agent actions.
Audit Metadata