openspec-proposal

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied feature descriptions and includes them in generated markdown files. This is a potential surface for indirect prompt injection if those files are later interpreted as instructions by an AI agent.\n- Ingestion points: The <feature description> parameter provided by the user in the command /openspec-proposal.\n- Boundary markers: No delimiters are used to separate user input from template structure in the generated files.\n- Capability inventory: The skill uses Read, Write, Glob, Grep, and Bash (for mkdir) to manage project files.\n- Sanitization: Path traversal is mitigated by the instruction to convert user input to 'kebab-case' for directory names.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 09:08 PM