openspec-generate-specs
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting and processing untrusted data to generate documentation.\n- Ingestion points: Local project files (src/, docs/) and remote GitHub issues/PRs fetched via MCP tools.\n- Boundary markers: Absent; the skill does not wrap ingested content in delimiters or include instructions to ignore embedded commands.\n- Capability inventory: The agent can read/write files and execute shell commands (mkdir, openspec).\n- Sanitization: Not performed; external content is interpolated directly into the generated markdown files.\n- [COMMAND_EXECUTION]: The skill uses shell commands to manage the filesystem and validate results.\n- Executes 'mkdir -p' to create directories based on identified capability names.\n- Executes 'openspec validate --specs --json' to verify the generated specification files.
Audit Metadata