performance-blocking
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input data from external files which could theoretically influence the agent's behavior if malicious instructions were embedded in the source material.
- Ingestion points: Reads core contract, CHARACTER_PROFILE.md, PERFORMANCE_BLOCKING.md, screenplay, line manifest, and other production documents (SKILL.md).
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the ingested data are specified.
- Capability inventory: The skill is limited to reading files and writing structured staging data to 03_preproduction/performance_blocking.jsonl. It does not possess network, subprocess, or dynamic execution capabilities.
- Sanitization: No validation or sanitization mechanisms for the input content are described.
- [SAFE]: The skill operates within a restricted execution scope as defined by the disable-model-invocation frontmatter. It follows standard pre-production workflows and utilizes local file paths for its operations.
Audit Metadata