pdd-setup
Fail
Audited by Snyk on Nov 21, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill's instructions are a narrow, disclosed setup task (one marked block in CLAUDE.md/AGENTS.md and a .gitignore entry), but line 10 says the
pdd setupcommand it describes installs skills and updates marked copies without a user request, which conflicts with the claim that the skill installs nothing.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required steps only edit the repo's own CLAUDE.md/AGENTS.md and .gitignore and read bundled references, but the
pdd setupcommand it invokes may install or update skills from an unspecified public source, which is a low-risk package path.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill edits persistent agent instruction files (CLAUDE.md/AGENTS.md) and the repo's .gitignore, and references a
pdd setupcommand that installs skills and previews MCP changes, which is an operational change, but no irreversible operational loss is established because the edit replaces only the marked PDD block and preserves all other text.
Issues (3)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata