spec-system-map
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests untrusted data from the repository to map system architecture. Ingestion points: Reads spec/charter.md, README.md, AGENTS.md, CLAUDE.md, and project configuration files. Boundary markers: No specific markers are implemented to delimit external content within the agent's context. Capability inventory: The skill is limited to file system reads and documentation writes (spec/system-map.md) and does not engage in network or shell execution. Sanitization: No explicit sanitization or validation of repository content is performed before processing.
- [SAFE]: Comprehensive analysis of the instructions, metadata, and templates identified no obfuscation, hardcoded credentials, or remote code execution patterns. The skill restricts its scope to documentation management using local project signals.
Audit Metadata