wiki-update

Pass

Audited by Gen Agent Trust Hub on May 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes git log commands to identify recent changes and commit history in the project being synchronized.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection risks due to its core function of distilling untrusted data into documentation.
  • Ingestion points: Processes content from project README.md files, source code, dependency manifests, and git logs (SKILL.md).
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are used when processing the ingested project data.
  • Capability inventory: Performs local file write operations to the Obsidian vault and executes git commands.
  • Sanitization: The skill does not implement sanitization or validation of the content gathered from the project environment before it is used for wiki generation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 6, 2026, 08:38 PM