paw-cra-multi-platform-export
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes external command-line utilities
ffmpegandffprobefor media analysis and transformation. It constructs shell commands based on asset properties and platform-specific requirements found inreferences/platform-export-specs.md. These commands are integral to the skill's primary function of media processing. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources, creating a potential surface for indirect prompt injection.
- Ingestion points: The workflow reads master assets and campaign metadata from
{project-root}/.pawbytes/creative-suites/index.md. - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the campaign brief data.
- Capability inventory: The skill has the capability to execute shell commands via
ffmpegandffprobeand perform filesystem write operations for export manifests and daily logs. - Sanitization: The instructions do not define specific sanitization or validation routines for text extracted from campaign briefs before it is used in the workflow.
Audit Metadata