tech-spec
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary function involves reading local project files and documentation (e.g.,
../coding-standards/SKILL.md) to generate technical design specifications. This localized file access is necessary for the skill's operation and does not involve access to sensitive system paths or network exfiltration. - [PROMPT_INJECTION]: The skill processes potentially untrusted input from conversations and codebases (Indirect Prompt Injection surface). However, the instructions explicitly restrict the agent to design tasks and forbid implementation ('Do not implement'), which significantly reduces the risk of malicious instructions being executed.
- Ingestion points: Conversation context, local documentation, and codebase inspection (SKILL.md).
- Boundary markers: None explicitly defined to separate untrusted data from instructions.
- Capability inventory: File system read access and user-triggered file system write access.
- Sanitization: No explicit sanitization or filtering of input data is performed.
Audit Metadata