skills/bklit/bklit-ui/wiki-llms-txt/Gen Agent Trust Hub

wiki-llms-txt

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes 'git remote get-url origin' and 'git rev-parse --abbrev-ref HEAD' to gather repository metadata such as the origin URL and current branch name.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via the aggregation of wiki content into the 'llms-full.txt' file.
  • Ingestion points: All markdown files located in the 'wiki/' directory.
  • Boundary markers: The skill uses '' tags to delimit individual pages in the consolidated output.
  • Capability inventory: The skill performs file writes to create 'llms.txt', 'wiki/llms.txt', and 'wiki/llms-full.txt'.
  • Sanitization: The process strips YAML frontmatter but lacks content filtering or sanitization for instructions embedded within the markdown text.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 08:03 PM
Security Audit — agent-trust-hub — wiki-llms-txt