onenote-rate-limits
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process external data, including Microsoft Graph OneNote API responses and documentation, to determine throttling strategies. This creates a potential surface for indirect prompt injection if an attacker can influence the content of these external resources.\n
- Ingestion points: Microsoft Graph OneNote API 429 error responses and documentation referenced in
references/official-docs.md.\n - Boundary markers: The instructions in
SKILL.mddo not specify explicit delimiters to isolate external data from the agent's core instructions.\n - Capability inventory: As defined in
SKILL.md, the agent usesRead,Glob,Grep,Write, andEdittools to inspect the environment and modify repository files.\n - Sanitization: The skill includes defensive measures such as redacting request evidence and quarantining ambiguous writes as noted in
references/official-docs.mdandSKILL.md.\n- [NO_CODE]: The skill consists solely of markdown instructions and references; no executable scripts or binaries are included.
Audit Metadata