studio-social
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from user-provided master scripts to generate social media content. This represents a standard indirect injection surface where instructions embedded in the master script could potentially influence the LLM's output.\n
- Ingestion points: Master script JSON files are read from the filesystem via the --script CLI argument in scripts/lib/run.mjs.\n
- Boundary markers: Prompt templates in scripts/lib/prompts.mjs interpolate script content directly without specialized boundary delimiters.\n
- Capability inventory: The skill is capable of writing draft and usage log files to the filesystem and making network requests for text generation via OpenRouter.\n
- Sanitization: The input script is parsed as JSON and strictly validated against specific schemas in scripts/lib/schema.mjs before being processed.
Audit Metadata