drama-skills

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves analyzing untrusted external data, creating a surface for indirect prompt injection attacks.
  • Ingestion points: Long-form novels and chapter analysis are ingested for adaptation triage, and episode screenplays are processed during the writing and asset extraction stages (SKILL.md, references/workflow-and-routing.md).
  • Boundary markers: Step 2.4 of SKILL.md explicitly instructs the agent to treat external corpora as data rather than instructions, which provides a level of mitigation against accidental obedience.
  • Capability inventory: The skill utilizes Bash, Write, and Edit tools to manage project files and derive creative documents, representing a capability tier that could be exploited if an injection is successful.
  • Sanitization: There is no documented evidence of input sanitization or filtering for the external text content processed by the toolset.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 11:33 PM
Security Audit — agent-trust-hub — drama-skills