skills/firecrawl/openclaw/sag/Gen Agent Trust Hub

sag

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the sag binary from a third-party Homebrew tap (steipete/tap/sag). This is the primary dependency for the skill's functionality.
  • [COMMAND_EXECUTION]: The skill executes the sag command-line tool to convert text to speech and list available voices.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied strings as input for the sag command. The ingestion point is the text passed to the CLI. While standard quoting is used in examples, untrusted data could theoretically attempt to escape the command string if not properly handled by the agent's execution environment. The skill uses /tmp/voice-reply.mp3 as a temporary storage path for the generated output.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:53 PM
Security Audit — agent-trust-hub — sag