skillpack-admin
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted metadata from external source files during the skill discovery process.
- Ingestion points: The
discoverSkillsfunction inscripts/lib.mjsreads the content ofSKILL.mdfiles from audited directories. - Boundary markers: None present; the script parses the raw content of the markdown files to extract YAML frontmatter.
- Capability inventory: The skill has significant file system capabilities, including recursive directory creation and file copying through
copyTreeOverlayinscripts/lib.mjs. - Sanitization: The skill applies a strict regex pattern (
NAME_PATTERN) to validate extracted skill names before using them in file paths, which effectively prevents directory traversal or command injection via this metadata. - [COMMAND_EXECUTION]: The skill includes scripts that perform extensive file system operations (read, write, copy, hash) based on user-provided command-line arguments.
- Evidence: The
scripts/adopt.mjsandscripts/lib.mjsfiles implement logic to copy entire directory trees (copyTreeOverlay). - Mitigation: The implementation includes multiple security assertions, such as
assertBoundedTargetto prevent operations on the filesystem root, andassertNoSymlinkAncestors/assertNoSymlinkBelowto prevent symbolic link attacks.
Audit Metadata