adhd-daily-planner
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill architecture presents a surface for indirect prompt injection, as it is designed to ingest and process untrusted user data while maintaining high-privilege tool access.
- Ingestion points: User-supplied daily tasks, brain dump entries, and planning horizons processed as described in
SKILL.md. - Boundary markers: The skill instructions do not specify explicit delimiters or 'ignore embedded instructions' warnings for the processing of user data.
- Capability inventory: The agent is granted access to the
Bash,WebFetch,WebSearch, andWritetools in theSKILL.mdfrontmatter. - Sanitization: There is no evidence of specific sanitization, validation, or filtering of external/user-provided content before interpolation into agent prompts.
Audit Metadata