wiki-digest

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs legitimate knowledge management tasks within a local environment without any malicious patterns detected.
  • [PROMPT_INJECTION]: An indirect prompt injection surface exists as the skill reads untrusted markdown files from the vault.
  • Ingestion points: Reads content from all .md files under the user-defined $OBSIDIAN_VAULT_PATH (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when reading content for summarization.
  • Capability inventory: Capabilities are limited to local file read/write operations within the vault; no network or system command execution tools are present.
  • Sanitization: No content sanitization is performed on the ingested markdown data.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 02:56 AM