philosophy-distiller
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-supplied writing (essays, articles, notes) which acts as a vector for untrusted data.
- Ingestion points: The "Writing corpus" and optional "Existing PHILOSOPHY.md" identified in the Inputs section of SKILL.md.
- Boundary markers: The instructions do not establish explicit delimiters or include safety warnings to the agent regarding potential instructions embedded within the processed text.
- Capability inventory: The skill has the capability to write to the file system to create or update the PHILOSOPHY.md document based on analyzed content.
- Sanitization: No sanitization, escaping, or validation of the input corpus is performed prior to the analysis and distillation process.
Audit Metadata