api-recon

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 recon tool for an authorized engagement, but it disables TLS certificate verification for the user's own connections, which weakens a protection beyond what the task needs, though this is disclosed and not aimed at the user.

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

  • Third-party content exposure detected (low risk: 0.10). The required workflow fetches the user-specified target site's pages and API responses (spider_mpa.py crawls same-origin HTML; runtime_harvest.js loads routes and captures response bodies), so outsider-authored text could reach the agent only through pages it actively fetches from a site the user chose, not through an inbox or feed the workflow monitors.

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 insert_assets step writes service and endpoint assets into an asset store, which changes a system supporting ongoing work, but no explicit irreversible operational loss is shown, so the change is capped at low.

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, 10:04 AM
Issues
3