generate-edit-decision-list

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data, including transcriptions and scene descriptions, which are interpreted by the agent to create the final Edit Decision List (edl.json). This creates a potential surface for indirect prompt injection where instructions hidden in user data could manipulate the agent's planning logic. \n
  • Ingestion points: The skill reads from user-provided script_source, words_json, and scene_table inputs. \n
  • Boundary markers: The workflow does not define specific delimiters or instructions to ignore potential commands embedded in the ingested text. \n
  • Capability inventory: The skill relies on local script execution (edl_pacing.py, edl_validate.py) and standard file-writing capabilities. \n
  • Sanitization: No programmatic sanitization or validation of the input text content is performed before interpolation into the generated EDL fields.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 04:39 PM
Security Audit — agent-trust-hub — generate-edit-decision-list