siyu-restore

Pass

Audited by Gen Agent Trust Hub on Nov 2, 2026

Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill accesses files in ~/.siyu/clients/, which is a vendor-owned resource directory for the author's suite of tools. This access is consistent with its primary purpose of managing customer archives but involves reading data from the user's home directory.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted markdown data from local files which influences the agent's state and next actions.
  • Ingestion points: Markdown archives located in ~/.siyu/clients/.
  • Boundary markers: Absent; the instructions do not require the use of delimiters or ignore-instructions warnings for the imported data.
  • Capability inventory: The skill uses file-reading capabilities and relies on the next_skill metadata field within the archives to determine the agent's workflow.
  • Sanitization: Absent; archive content is presented and acted upon without explicit sanitization or content validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 2, 2026, 02:07 AM