skills/akillness/jeo-skills/leann/Gen Agent Trust Hub

leann

Pass

Audited by Gen Agent Trust Hub on Oct 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to perform local repository inspection and interact with the leann CLI for document indexing and retrieval.
  • [EXTERNAL_DOWNLOADS]: The documentation provides instructions to install the leann package via uv pip install, referencing official package registries for the tool's dependencies.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted text data to generate vector embeddings, presenting a potential surface for indirect prompt injection if source files contain adversarial instructions.
  • Ingestion points: Local document files are read by the leann build command as specified in SKILL.md and the upstream references.
  • Boundary markers: The skill relies on user-driven scoping of input directories; explicit prompt delimiters for document content are not provided in the skill instructions.
  • Capability inventory: The skill employs Bash for operational commands and a local Python script for repository verification.
  • Sanitization: The scripts/preflight.py utility includes strict path validation and a blocklist (e.g., .ssh, .aws, .env) to prevent accidental ingestion of sensitive credentials during the verify step.
  • [SAFE]: The included preflight.py script implements robust security practices, including the use of os.O_NOFOLLOW and directory-relative file descriptors to mitigate symbolic link attacks and race conditions during file verification.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 30, 2026, 09:02 AM