study-habits
Warn
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: MEDIUMMETADATA_POISONINGINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [METADATA_POISONING]: The author name 'clawd-team' is deceptive as it does not match the identified vendor 'sundial-org' and appears to be a variant of 'Claude'.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided strings for study topics and logs. 1. Ingestion points: User input for study session topics and confidence ratings in SKILL.md. 2. Boundary markers: Absent from the prompt instructions. 3. Capability inventory: No tools or code execution capabilities are present. 4. Sanitization: No explicit validation or filtering is specified.
- [NO_CODE]: This skill contains only documentation and natural language triggers without executable code or scripts.
Audit Metadata