sdlc-create-plan
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected. The skill is strictly instructional and focused on project management tasks.
- [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill reads external content from
intent.mdandspec.mdfiles located within the work-item directory. - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined for the input data.
- Capability inventory: The skill is restricted to reading workspace files and writing a single documentation file (
plan.md). It explicitly forbids modifying production code or creating other artifacts. - Sanitization: No sanitization or validation of the input markdown files is performed.
- Note: The lack of dangerous capabilities (command execution, network access) ensures that any potential injection within the input documents has minimal security impact.
Audit Metadata