content-curator
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from an Obsidian vault, which constitutes untrusted external data. While the skill is designed for curation, malicious instructions embedded within notes could theoretically influence agent behavior.
- Ingestion points: Notes are read using the Read, Grep, and Glob tools as part of the curation workflow in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions found within the vault notes.
- Capability inventory: The skill possesses Write and Edit capabilities, enabling it to modify or delete files based on its evaluation.
- Sanitization: The skill lacks explicit sanitization or validation of note content before processing.
Audit Metadata