skill-library-sync

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides numerous shell commands for file management and system operations across sensitive directories like ~/.agents, ~/.claude, and ~/.hermes.
  • Evidence includes instructions to use mv, ln -sfn for symbolic links, rsync -a --delete for mirroring, and tar for archiving.
  • Mentions execution of a custom synchronization script ~/.agents/sync-to-claude.sh with flags that overwrite local files.
  • [EXTERNAL_DOWNLOADS]: Describes a process for downloading and integrating third-party code from external registries.
  • Instructions detail using npm pack to download package payloads and tar xzf to extract them into the skill library for subsequent execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill manages instruction sets (skills) from external sources, creating a potential surface for ingesting malicious commands into the agent environment.
  • Ingestion points: Third-party skills downloaded via npm or imported as "portable kits."
  • Boundary markers: The skill relies on manual review and documentation rather than programmatic delimiters to isolate external instructions.
  • Capability inventory: The environment supports powerful file operations, symbolic linking, and script execution via python3 and node.
  • Sanitization: Provides specific techniques for redacting sensitive information using sed and verifying the absence of leaked tokens with rg (ripgrep).
  • Security Bypass: Instructs users or agents to add files to ~/.hermes/skillgate/self-owned.list specifically to exempt them from automated security scanning by the platform's "watchdog" service.
  • [DATA_EXFILTRATION]: Explicitly identifies the risk of "fugas" (data leaks) when sharing skills with third parties.
  • Acknowledges that managed files may contain sensitive identifiers such as client names, internal brands, tokens, and absolute file paths, and provides a procedure to identify and remove them.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 10:26 AM