skills/tuongaz/skills/wiki-ingest/Gen Agent Trust Hub

wiki-ingest

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the git mv command to move source files into the wiki's internal directory structure (e.g., raw/articles, raw/papers) if the wiki is a git repository.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting untrusted external data (articles, papers, book chapters, transcripts) to generate summaries and update wiki pages.
  • Ingestion points: SKILL.md (Workflow Step 2: Reads the source file).
  • Boundary markers: Absent; the instructions do not specify delimiters or warnings to ignore instructions that might be embedded within the processed source material.
  • Capability inventory: The agent has permissions to read local files, execute git commands for file movement, and write or append to various markdown files within the wiki root.
  • Sanitization: Absent; the skill is instructed to summarize content and extract key claims directly from the untrusted source files without filtering for malicious directives.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 12:10 PM
Security Audit — agent-trust-hub — wiki-ingest