x-post-creator-skill
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's feedback integration protocol creates a vulnerability surface for indirect prompt injection.
- Ingestion points: The agent is instructed to read the content of
references/feedback-log.mdat the start of every generation task to incorporate 'accumulated learnings'. - Boundary markers: No delimiters or instructions are provided to help the agent distinguish between benign feedback and malicious instructions embedded within the feedback log.
- Capability inventory: The skill possesses file-read and file-append capabilities specifically for the
references/feedback-log.mdfile. - Sanitization: User feedback is collected and appended to the log without any validation or sanitization, and the instructions explicitly command the agent to 'apply immediately to all future generations'.
Audit Metadata