architecture-blueprint-generator
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because its core workflow involves the deep analysis of untrusted files from an external codebase, which could contain malicious instructions designed to influence the agent's behavior during document generation.
- Ingestion points: Project configuration files, package dependencies, and framework-specific patterns defined in SKILL.md (Workflow Step 1) and references/blueprint-structure.md (Section 1).
- Boundary markers: No explicit delimiters or warnings to ignore embedded instructions are provided when processing external content.
- Capability inventory: The agent performs extensive file reading and text generation/formatting.
- Sanitization: There are no instructions to sanitize or filter the input data before it is used to generate the final blueprint.
- [DATA_EXFILTRATION]: The instructions for documenting the architecture include sensitive areas such as 'secret management approach' and 'configuration management', which could lead to accidental exposure of security patterns or sensitive file paths in the generated output.
- Evidence: references/blueprint-structure.md (Section 7) directs the agent to document 'configuration source patterns', 'environment-specific strategies', and 'secret management approach', which requires the agent to inspect sensitive parts of the project configuration.
Audit Metadata