Security audit
Security checks for vulnerabilities and agentic risk
The skill openly enables Talentir payouts, but it also gives agents high-impact payment and webhook administration commands without clear approval safeguards.
Install only if you intend agents to have payment authority through Talentir. Use a narrowly scoped API key, keep daily limits low, disable payout auto-approval unless explicitly needed, and require human review for every payout and any webhook creation or deletion.
The skill is presented as a payment tool, but it also documents access to team/account information and full webhook management. This broader capability increases the attack surface and can mislead downstream agents or users into granting or using permissions beyond the narrow payout purpose.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
All requests need:
curl -s "https://www.talentir.com/api/v1/..." \
-H "Authorization: Bearer $TALENTIR_API_KEY" \
-H "Content-Type: application/json"
The skill provides ready-to-run examples for creating payouts and deleting webhooks without prominent warnings about financial impact or system changes. In an agent context, this increases the likelihood of unsafe execution because destructive or money-moving actions are normalized as routine examples.
This example sends payout instructions and recipient identifiers to an external service, directly enabling transfer of funds. In the context of an autonomous agent skill, this is dangerous because misuse or prompt-driven execution can cause unauthorized financial transactions and disclosure of recipient data.
Supported platforms: tiktok, instagram, youtube-channel.
curl -s -X POST "https://www.talentir.com/api/v1/payout" \
-H "Authorization: Bearer $TALENTIR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
This variant also performs an external payout request and additionally includes tags and custom identifiers that could expose business metadata. The main risk is still unauthorized financial transfer, amplified by the richer metadata being transmitted externally.
curl -s -X POST "https://www.talentir.com/api/v1/payout" \
-H "Authorization: Bearer $TALENTIR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
Webhook creation and deletion are administrative capabilities unrelated to simple direct payments and can materially alter account integrations. An agent with this skill could add exfiltration endpoints or remove legitimate monitoring/integration hooks, causing data leakage or operational disruption.
Creating a webhook transmits configuration to an external service and establishes a persistent outbound event channel to a target URL. If abused, this can redirect sensitive payout event data to attacker-controlled infrastructure and create durable exfiltration paths.
curl -s -X POST "https://www.talentir.com/api/v1/webhook" \
-H "Authorization: Bearer $TALENTIR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
The documented preApproved option enables auto-approval of payouts, reducing friction for autonomous money movement. In an agent setting, this meaningfully increases the chance that an unintended or manipulated action results in immediate financial impact without a review checkpoint.
| `tags` | No | Array of strings for categorization |
| `customId` | No | Your own identifier for the payout |
| `notifications` | No | `allowed` (default) or `not-allowed` |
| `preApproved` | No | `true` to auto-approve (requires `payout.api_approve` permission) |
## Payout Statuses
Team information access exceeds the stated payment-focused purpose and exposes organizational metadata that may aid reconnaissance. While less severe than payout or webhook actions, it still broadens available sensitive information without clear necessity.
No suspicious patterns detected.