shot-list
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from user-provided screenplay files which are parsed to drive the agent's collaborative workflow. This creates a surface for instructions embedded in the scripts to influence the agent's actions.
- Ingestion points: Screenplay files in .fountain, .fdx, and .txt formats are processed by
scripts/parse_screenplay.pyandSKILL.md. - Boundary markers: There are no specific delimiters or warnings used to separate extracted script content from the agent's system instructions during the analysis phase.
- Capability inventory: The skill performs filesystem writes to generate PDF files in
/mnt/user-data/outputs/usingscripts/generate_shot_list_pdf.py. - Sanitization: No sanitization or validation is performed on the text extracted from the scripts to prevent prompt injection attacks.
Audit Metadata