drama-analysis
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface (Category 8) because its primary function is to analyze untrusted external content.\n
- Ingestion points: Untrusted data enters the agent context through user-provided drama fragments, novel chapters, and IP concepts, or via the
load_artifacttool as described inSKILL.md.\n - Boundary markers: No specific delimiters or safety warnings (e.g., "ignore embedded instructions") are defined to separate the untrusted input from the agent's analytical instructions.\n
- Capability inventory: The skill is capable of modifying the local filesystem using a
Writetool to save JSON analysis toprojects/<slug>/state/analysis/and useslog_decisionfor audit logging as specified inSKILL.md.\n - Sanitization: There is no evidence of input validation, escaping, or filtering of the ingested drama content before it is processed by the agent.
Audit Metadata