sf-symbols-finder
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
sfsymbolsCLI tool located at the path/Applications/SF Symbols.app/Contents/Executables/sfsymbolsto perform icon searches and compatibility checks. - [INDIRECT_PROMPT_INJECTION]: The skill instructions facilitate an environment where user-provided natural language input is directly incorporated into shell command arguments.
- Ingestion points: User-provided interface element descriptions used for semantic search within
SKILL.md. - Boundary markers: The provided command examples use double quotes for the search string, which helps with word splitting but does not prevent subshell execution (e.g., using
$()or backticks). No explicit instructions are given to the agent to treat input as literal text or to ignore shell metacharacters. - Capability inventory: Execution of shell commands via the local
sfsymbolsbinary as described inSKILL.md. - Sanitization: Absent. There are no instructions for the agent to escape shell metacharacters, validate input length, or filter dangerous characters before execution.
Audit Metadata