skills/sd0xdev/sd0x-harness/dep-audit/Gen Agent Trust Hub

dep-audit

Warn

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill interpolates user-supplied $ARGUMENTS directly into a shell command (bash .claude/scripts/dep-audit.sh $ARGUMENTS), which creates a potential surface for shell command injection if the input is not sanitized by the platform.\n- [REMOTE_CODE_EXECUTION]: The skill invokes npx yarn-audit-fix, which downloads and executes code from the npm registry. While this targets a well-known service, it involves the execution of remote code.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from project manifest files and tool outputs.\n
  • Ingestion points: Project manifest files (e.g., package.json, pyproject.toml, go.mod) and the stdout/stderr of auditing tools (SKILL.md).\n
  • Boundary markers: None identified to separate untrusted data from instructions.\n
  • Capability inventory: Shell command execution, file system reads, and file system writes (when the --fix argument is used) (SKILL.md).\n
  • Sanitization: No explicit sanitization or validation of manifest content or tool output is specified.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 24, 2026, 01:44 PM
Security Audit — agent-trust-hub — dep-audit