the-sit-down
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill functions by synthesizing information from external intelligence sources, creating a surface for indirect instructions.
- Ingestion points: Processes content from the Reconnaissance Dossier, Grilling Consensus, Project Constitution, and Ledger entries in
SKILL.mdStep 1. - Boundary markers: Absent. The instructions do not specify delimiters to separate untrusted data from the agent's instructions.
- Capability inventory: The skill can read and write files in the local file system (
docs/gangsta/directory) and trigger other agent phases. - Sanitization: Absent. No explicit sanitization or escaping of ingested data is prescribed.
- [COMMAND_EXECUTION]: The skill directs the agent to automate the transition between workflow phases, reducing the number of manual user confirmation steps.
- Evidence: Step 5 mandates that the agent "Immediately invoke gangsta:resource-development — do NOT ask the Don what to do next, do NOT pause, do NOT prompt for confirmation."
Audit Metadata