content-reflection
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and does not contain any executable scripts, shell commands, or network operations. There are no external dependencies or remote code execution patterns.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze untrusted user-supplied content (drafts, tweets, newsletters), which presents a potential surface for indirect instructions.
- Ingestion points: User-provided content entered for review as described in Step 1 and Step 2 of the Reflection Process in SKILL.md.
- Boundary markers: The instructions do not define explicit delimiters or security markers to isolate the user content from the system's evaluation logic.
- Capability inventory: While the skill body mentions integration with external tools like PubMed and Perplexity for verification, no sensitive system capabilities (such as local file writing or arbitrary command execution) are present in the skill configuration.
- Sanitization: There are no instructions for sanitizing or escaping user-provided text before the analysis is performed.
Audit Metadata