poster-storyline-builder
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides legitimate academic poster planning guidance and does not contain any malicious instructions, obfuscated code, or unauthorized network/file operations.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided manuscripts, which constitutes a data ingestion attack surface.
- Ingestion points: User-supplied research abstracts, manuscripts, and study summaries in SKILL.md.
- Boundary markers: Absent; there are no delimiters to separate user data from system instructions.
- Capability inventory: None; the skill generates text output only and does not possess capabilities for file modification, network communication, or shell command execution.
- Sanitization: No sanitization or validation is performed on the ingested research content.
Audit Metadata