ClawHub
Back to skill

Security audit

reply-to-every-review

Security checks for vulnerabilities and agentic risk

Overview

The skill fits review management, but its optional scheduled mode can publish replies without the individual approval it promises.

Start with interactive drafts for a selected app. Before enabling scheduling, enforce mandatory human approval or remove automatic apply_action calls. Check auto-apply rules and credit costs, protect API keys, and pin the downloaded playbooks to a reviewed revision.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Unattended automation can post replies without the user approving the individual drafts.

High
Category
Excessive Agency
Confidence
99% confidence
Finding

The unattended workflow calls apply_action on passing drafts without individual user approval, despite the skill's stated approval requirement. The skill explicitly acknowledges that an existing Studio auto-apply rule can cause these calls to publish immediately, so a passing guardrail score can replace human review and expose the app to unintended public statements. This is conditional on organization configuration; organizations that enforce manual approval retain that protection.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 143)May include surrounding context.

md
cp -r /tmp/appgoat-skills/skills/* .claude/skills/
          # Hosted AppGoat MCP server; the key goes into a file, not the command line.
          jq -n --arg key "$APPGOAT_API_KEY" \
            '{mcpServers: {appgoat: {type: "http", url: "https://api.appgoat.ai/mcp", headers: {"x-api-key": $key}}}}' \
            > "$RUNNER_TEMP/appgoat-mcp.json"
      - uses: anthropics/claude-code-action@v1
        with:

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · reference/api.md (reported line 3)May include surrounding context.

md
# REST fallback

Without the AppGoat MCP server, call the API directly. Base URL `https://api.appgoat.ai/v1`,
header `x-api-key: $APPGOAT_API_KEY` (create a key at https://dash.appgoat.ai). Responses are
`{ "data": …, "meta": { "credits_used", "credits_remaining", "next_cursor", … } }`; errors are
`{ "error": { "code", "message", "hint", "approve_url"? } }` - read `hint`.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · reference/api.md (reported line 20)May include surrounding context.

bash
CON=con_x8Hq2mXc0aLpQwRtYb APP=1234567890
curl -s -G -H "x-api-key: $APPGOAT_API_KEY" "https://api.appgoat.ai/v1/connections/$CON/reviews" \
  -d app=$APP -d unanswered=true -d limit=100 \
  | jq -r '.data[] | "\(.rating)★ \(.created_at[0:10]) \(.id) \(.body[0:160])"'

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · reference/api.md (reported line 25)May include surrounding context.

md
| jq -r '.data[] | "\(.rating)★ \(.created_at[0:10]) \(.id) \(.body[0:160])"'

curl -s -H "x-api-key: $APPGOAT_API_KEY" -H "content-type: application/json" \
  https://api.appgoat.ai/v1/actions -d @- <<JSON | jq '.data | {id, status, diff, guardrail}'
{"type":"review.reply","connection":"$CON","dry_run":true,"source":"playbook:reply-to-every-review",
 "params":{"app":"$APP","review_id":"<id>","text":"Thanks for the detailed report! …"}}
JSON

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 · reference/api.md (reported line 20)May include surrounding context.

bash
CON=con_x8Hq2mXc0aLpQwRtYb APP=1234567890
curl -s -G -H "x-api-key: $APPGOAT_API_KEY" "https://api.appgoat.ai/v1/connections/$CON/reviews" \
  -d app=$APP -d unanswered=true -d limit=100 \
  | jq -r '.data[] | "\(.rating)★ \(.created_at[0:10]) \(.id) \(.body[0:160])"'

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 · reference/api.md (reported line 24)May include surrounding context.

md
-d app=$APP -d unanswered=true -d limit=100 \
  | jq -r '.data[] | "\(.rating)★ \(.created_at[0:10]) \(.id) \(.body[0:160])"'

curl -s -H "x-api-key: $APPGOAT_API_KEY" -H "content-type: application/json" \
  https://api.appgoat.ai/v1/actions -d @- <<JSON | jq '.data | {id, status, diff, guardrail}'
{"type":"review.reply","connection":"$CON","dry_run":true,"source":"playbook:reply-to-every-review",
 "params":{"app":"$APP","review_id":"<id>","text":"Thanks for the detailed report! …"}}

Static analysis

No suspicious patterns detected.