the-switch-angle

Pass

Audited by Gen Agent Trust Hub on Jul 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is composed entirely of markdown text. It does not include any scripts, executables, or subprocess calls that would pose a risk to the host system or environment.- [PROMPT_INJECTION]: The skill is designed to process untrusted data (prospect tool stacks and product descriptions) provided by the user. While this represents a surface for indirect prompt injection, the skill lacks the capabilities (such as tool usage, file writing, or network access) that would be required to execute an attack.\n
  • Ingestion points: User-provided stack data and product descriptions requested in SKILL.md.\n
  • Boundary markers: Absent; the instructions rely on LLM reasoning and internal rules like the 'Anti-hallucination rule' rather than technical delimiters.\n
  • Capability inventory: None; the skill does not request or define any tools or script execution privileges.\n
  • Sanitization: Absent; there are no instructions for filtering or validating the user-provided stack data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 26, 2026, 12:19 PM