tidas-contract-context
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
tiangong-lcaCLI to perform dataset operations. It executes commands to generate context packs and retrieve contract artifacts, writing results to the local task workspace. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves fetching external artifacts that are subsequently processed by the AI agent, creating a potential surface for indirect prompt injection.
- Ingestion points: Data files such as
schema.json,methodology.yaml,runtime-ruleset.json,ai-context.json, andai-context.mdfetched via CLI as described in the verification section of SKILL.md. - Boundary markers: No specific boundary markers or 'ignore' instructions are implemented to isolate the fetched content.
- Capability inventory: The agent can execute CLI commands and verify file existence on the disk.
- Sanitization: No content sanitization or validation of the fetched artifacts is specified before they are read into the agent context.
Audit Metadata