skills/ruvnet/ruflo/sparc-spec/Gen Agent Trust Hub

sparc-spec

Pass

Audited by Gen Agent Trust Hub on Oct 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local codebase and user-provided descriptions, which could contain instructions intended to influence the agent's behavior.
  • Ingestion points: The skill reads feature descriptions from the $ARGUMENTS variable and analyzes existing files in the local codebase using the Read tool.
  • Boundary markers: No specific delimiters or instructions (like 'ignore embedded commands') are defined to isolate the ingested content from the skill's operational instructions.
  • Capability inventory: The skill has access to powerful tools including Bash, Edit, and persistent memory storage (mcp__plugin_ruflo-core_ruflo__memory_store).
  • Sanitization: The workflow does not include explicit validation or sanitization of the data retrieved from the codebase or the user input before it is used to generate the final specification or stored in memory.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 30, 2026, 04:38 AM