algorithm-design
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides structured guidance and templates for generating LaTeX pseudocode and Mermaid diagrams. A review of the instructions and reference templates in references/algorithm-templates.md confirms the absence of malicious logic, obfuscation, or unauthorized access attempts.\n- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests user-provided method descriptions.\n
- Ingestion points: The skill accepts input via the
$0argument (Method description or implementation) in SKILL.md.\n - Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the embedded data as data only or to ignore embedded instructions.\n
- Capability inventory: Based on the files provided (SKILL.md and references/algorithm-templates.md), the skill is limited to text generation and does not have the ability to execute shell commands, perform network requests, or modify the file system.\n
- Sanitization: No input validation or sanitization logic is implemented in the skill. However, the lack of privileged capabilities minimizes the potential impact of an injection attack.
Audit Metadata