grad-affordance
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: A comprehensive analysis of the skill's instructions and associated example scenario reveals no malicious patterns, command injections, or unauthorized resource access. The content is strictly limited to providing a theoretical framework and methodological steps for applying Affordance Theory.\n- [NO_CODE]: The skill is composed entirely of informational Markdown text and templates. There are no Python scripts, Node.js packages, shell commands, or network operations defined within the analyzed files (SKILL.md and sample_scenario.md).\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided artifact descriptions and actor profiles, creating an untrusted data ingestion surface. However, the complete lack of technical capabilities (no file system access, network communication, or code execution) ensures this surface cannot be exploited to perform harmful actions.\n
- Ingestion points: User-supplied technology descriptions and organizational scenarios processed through the methodology outlined in SKILL.md.\n
- Boundary markers: Absent; the skill relies on natural language instructions without explicit delimiters for untrusted data.\n
- Capability inventory: None; the skill's operations are limited to text-based analytical output with no tool usage or system-level access.\n
- Sanitization: Absent; no validation or filtering is performed on the input text.
Audit Metadata