seedance-camera

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to load and process several local reference files, creating a vulnerability surface for indirect prompt injection if those files were to contain malicious instructions.
  • Ingestion points: The skill loads content from ../../references/directors-read.md, ../../references/quick-ref.md, ../../references/cinematography-shot-language.md, ../../references/directing-engine.md, and multilingual vocabularies.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore potentially conflicting or malicious directions within the ingested reference files.
  • Capability inventory: The skill is purely instructional and does not utilize any subprocess execution, file writing, or network operations tools.
  • Sanitization: No explicit sanitization or validation of the ingested reference data is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 02:42 AM
Security Audit — agent-trust-hub — seedance-camera