development-contract-system
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to create shell scripts (e.g.,
check-change-contracts.sh,set-feature-record-lifecycle.sh) and execute them during a testing phase (Phase 7). This execution is performed locally within the repository to verify the system's logic. - [PROMPT_INJECTION]: The skill describes a system that ingests and processes user-supplied Markdown files (feature records). This represents a surface for indirect prompt injection if the processing scripts are not carefully implemented.
- Ingestion points: Markdown files located in the
feature_records/directory (SKILL.md, Phase 4). - Boundary markers: No specific delimiters or safety warnings for the parser are defined in the instructions.
- Capability inventory: The agent has the capability to run the generated scripts and their associated tests (SKILL.md, Phase 7).
- Sanitization: The skill does not provide instructions for sanitizing or escaping the content of the feature records before processing.
Audit Metadata