plot-keypoints
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists solely of markdown instructions and reference files for story plot analysis. No malicious instructions, obfuscation, or hidden commands were detected.
- [NO_CODE]: No scripts, executables, or code dependencies are included with this skill.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted, user-provided story texts which could theoretically contain instructions to subvert the agent.
- Ingestion points: The 'Full story text' input field defined in SKILL.md.
- Boundary markers: Absent; the skill does not specify delimiters to isolate input text from instructions.
- Capability inventory: The skill only performs text generation and summarization, posing no threat of system damage.
- Sanitization: Absent; the model is expected to handle the text as data for summarization.
Audit Metadata