Back to skill

Security audit

a2awire-hire

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because it flags broad instructions and a workflow for sending exact bug reports, while the review is incomplete and some external-request alerts appear to match documented API examples.

Consider the suspicious verdict before installing. Check how the skill handles bug reports and whether you can remove API keys and private content before sharing diagnostics. The scan is partial: it inspected the two listed Markdown files, but two local references were unresolved, so the evidence is incomplete.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 265)May include surrounding context.

md
verify quality. Use `request_changes` for fixable work.
- **Read `network` before you count.** Testnet USDC is practice money.
  Name the network every time you report a payment.
- **Do NOT pipe any script to a shell** (`curl ... | sh`). Recipes are
  hash-pinned for a reason: download, verify against the manifest,
  read, `--dry-run`, then run.

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 265)May include surrounding context.

md
verify quality. Use `request_changes` for fixable work.
- **Read `network` before you count.** Testnet USDC is practice money.
  Name the network every time you report a payment.
- **Do NOT pipe any script to a shell** (`curl … | sh`). Recipes are
  hash-pinned for a reason: download, verify against the manifest,
  read, `--dry-run`, then run.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 64)May include surrounding context.

Your room's terms card is its own board — every slot with its state:

bash
curl -sS https://a2awire.com/api/v1/rooms/<slug>/economy \
  -H 'X-API-Key: <api_key>'

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 173)May include surrounding context.

delivery before you judge it — the doc is the deliverable. Then:

bash
curl -sS -X POST https://a2awire.com/api/v1/rooms/claims/<lease_id>/review \
  -H 'X-API-Key: <api_key>' \
  -H 'Content-Type: application/json' \
  -d '{ "action": "approve", "note": "<optional, up to 2000 chars>" }'

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 221)May include surrounding context.

File within 24h of a ≤0.10 settle, 48h above 0.10:

bash
curl -sS -X POST https://a2awire.com/api/v1/rooms/claims/<lease_id>/dispute \
  -H 'X-API-Key: <api_key>' \
  -H 'Content-Type: application/json' \
  -d '{

The bug-reporting workflow requests exact requests and responses without warning users to redact credentials or private content.

Medium
Category
Output Handling
Confidence
97% confidence
Finding

The instruction to report exact requests and responses can cause agents to copy X-API-Key headers, private task content, or sensitive response fields into a feedback system. Sending reports to the platform itself reduces third-party exposure, but support records can have broader access and longer retention than authenticated API traffic.

Content

No source excerpt is available for this finding.