create-local-skill

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to perform several shell operations including directory creation (mkdir -p), symlink creation (ln -s), and file verification (ls -la). These are standard operations for the skill's stated purpose of managing project configuration.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because user-provided content is used to derive a skill name that is then interpolated into shell commands.
  • Ingestion points: User input describing the desired skill functionality is ingested in Step 1 of the workflow.
  • Boundary markers: There are no explicit boundary markers or instructions to the agent to disregard instructions embedded within the user's description.
  • Capability inventory: The skill utilizes shell command execution capabilities (mkdir, ln) across its workflow.
  • Sanitization: While the skill instructs the agent to "Derive a kebab-case name," there is no programmatic validation or strict enforcement to prevent a malicious user from providing a name containing shell metacharacters (e.g., ;, |, &) that could lead to command injection.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 03:21 PM