vcr-style-skill-template
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to use the
vcrcommand-line tool for validating manifests (vcr check), rendering frames (vcr render-frame), and building video files (vcr build). these operations are essential to the primary function of the skill. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it ingests untrusted data from external files that influence its output and operations.
- Ingestion points: The skill reads configuration from
references/style_tokens.yamland scene definitions from user-provided.vcrfiles. - Boundary markers: No delimiters or explicit instructions are provided to ignore embedded commands or instructions within the text fields of the data files.
- Capability inventory: The skill reads local files and executes shell commands via the
vcrtool, which could be influenced by the data it processes. - Sanitization: No input validation, escaping, or sanitization of the content from the YAML or VCR files is mentioned in the workflow.
Audit Metadata