dialogue-timing-preflight
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script
scripts/dialogue_timing_preflight.py. This is a standard operation for the skill's stated purpose of dialogue validation. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from an external project file which creates a potential surface for indirect prompt injection.
- Ingestion points: The file
../../references/DIALOGUE_TIMING_PREFLIGHT.mdis read into the agent's context (referenced inSKILL.md). - Boundary markers: None identified in the provided instructions to separate the reference content from the agent's core instructions.
- Capability inventory: The skill has the capability to execute a Python script (
scripts/dialogue_timing_preflight.py) with aPROJECTargument. - Sanitization: No explicit sanitization or validation of the content from the reference file is mentioned.
- Ingestion points: The file
Audit Metadata