capacity-plan
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONMETADATA_POISONING
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze data from external project trackers and calendars, which may contain malicious instructions from third parties.
- Ingestion points: Data from project trackers and calendars (referenced in SKILL.md).
- Boundary markers: Absent; no instructions are provided to the agent to treat these inputs with specific delimiters or as untrusted.
- Capability inventory: None; the skill ships no code or tool definitions.
- Sanitization: Absent.
- [METADATA_POISONING]: The LICENSE file contains anomalous, deceptive text at the end ('recorded-cams', 'input()'). Although suspicious, it does not constitute a functional threat as it resides in a non-executable document.
Audit Metadata