ganjoor

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 is a documented read-only poetry tool, but its instruction to route traffic through an external HTTP proxy with an Iranian IP to work around 403s or timeouts could expose the user's requests to an unvetted intermediary, a risk the user would not expect, though nothing shows malicious intent.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (low risk: 0.10). The Ganjoor site serves community-contributed text, such as reader comments (gj_poem_extras) and couplet meanings (gj_poem), but the agent only reads it after searching for or selecting a specific poem, so an outsider cannot force delivery into the workflow.

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's setup branch gives concrete instructions to install an MCP server into the agent's configuration (claude mcp add ganjoor ... or editing the client's MCP servers config), which is a persistent integration change, but no explicit irreversible operational loss is established.

Issues (3)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 21, 2026, 05:05 PM
Issues
3