skills/security-phoenix-demo/security-skills-claude-code/phoenix-constraint-distiller/Gen Agent Trust Hub
phoenix-constraint-distiller
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input in the form of a SCOPE_DEFINITION to generate a set of constraints. It lacks specific instructions to ignore or delimit potentially malicious instructions embedded within that input data.\n
- Ingestion points: The skill processes SCOPE_DEFINITION as defined in the skill description and frontmatter.\n
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are present for the input data.\n
- Capability inventory: The skill primarily performs text distillation and does not exhibit high-risk capabilities like network access or arbitrary command execution.\n
- Sanitization: No explicit sanitization or validation of the input data is described.
Audit Metadata