ops-marketing

Fail

Audited by Snyk on Apr 29, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The skill explicitly scans for and prints environment/Doppler/Keychain entries (e.g., printenv, security -w, doppler secrets --plain) and requires presenting "ALL findings" and prompting for missing API keys which will be embedded into curl/CLI flows, meaning secrets can be output verbatim and thus exposed — high exfiltration risk.

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

  • Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly fetches and ingests untrusted, user-generated third‑party data (e.g., Meta/Instagram Graph API media and insights, Google Search Console queries/pages, Google Ads search terms and metrics, and arbitrary image/video URLs) and then uses that data in workflows that create/pause campaigns, set rules, compute optimizations, and recommend budget reallocations (see the meta-manage, instagram, seo/gsc, google-ads, campaigns, optimize, and attribution sections), so third‑party content can materially influence agent actions.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

  • Direct money access detected (high risk: 1.00). The skill explicitly integrates with advertising/payment-related APIs (Meta Graph API, Google Ads API) and provides commands that create and modify live ad spend and budgets. Examples: Meta "create-campaign" and "advantage" POSTs include daily_budget; meta "rules" can create automation with execution_spec that INCREASE_BUDGET; meta "creative" and "ads" endpoints create ads/adcreatives. Google Ads section performs campaignBudgets:mutate and campaign campaigns:mutate calls, supports "create campaign", "adjust budget", "enable/pause campaign", and updates campaignBudget.amountMicros via the API. These are specific, purpose-built operations to change advertising budgets and create/enable campaigns (i.e., directly affect spend). Under the CORE RULE this is Direct Financial Execution (managing ad spend budgets via API).

Issues (3)

W007
HIGH

Insecure credential handling detected in skill instructions.

W011
MEDIUM

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

W009
MEDIUM

Direct money access capability detected (payment gateways, crypto, banking).

Audit Metadata
Risk Level
HIGH
Analyzed
Apr 29, 2026, 06:48 AM
Issues
3