skills/ammar-hasan/agent-skills/sto/Gen Agent Trust Hub

sto

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill package does not contain any executable scripts, binaries, or command-line tools.
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as a surface for processing untrusted data, but the lack of executable capabilities mitigates risk. 1. Ingestion points: Untrusted data enters via the $ARGUMENTS variable and conversational history as defined in SKILL.md. 2. Boundary markers: No delimiters are present to separate instructions from data. 3. Capability inventory: The skill possesses no capabilities for network access, file system modification, or command execution. 4. Sanitization: No sanitization or validation is applied to the input data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 05:39 AM
Security Audit — agent-trust-hub — sto