plan-my-day
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONMETADATA_POISONINGNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where the agent ingests external data from the user's calendar and daily priorities, which creates a potential surface for indirect instructions to be processed.
- Ingestion points: Calendar commitments and user priorities (documented in
SKILL.md). - Boundary markers: Absent; there are no instructions for the agent to use delimiters when processing this data.
- Capability inventory: None; the skill does not define or use any tools, scripts, or network capabilities.
- Sanitization: Absent; the instructions do not specify any validation or filtering of the ingested calendar content.
- [METADATA_POISONING]: The skill exhibits inconsistent metadata regarding authorship and versioning across its files and execution context.
- Evidence: The author is variously listed as 'brianrwagner' (environment context), 'theflohart' (
SKILL.md), and 'itsflow' (_meta.json). Versioning is inconsistent betweenSKILL.md(3.0.0) and_meta.json(1.0.0). - [NO_CODE]: The skill is comprised entirely of Markdown-based instructions and metadata; it does not include any Python, Node.js, or shell scripts, eliminating the risk of direct malicious code execution.
Audit Metadata