ClawHub
Back to skill

Security audit

daily.dev Ask

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed daily.dev search helper that needs a user-provided API token and does not show hidden or destructive behavior.

Install only if you are comfortable letting the agent use your daily.dev API token and send your technical search queries to daily.dev. Prefer a scoped environment secret when available, and review the optional shell-profile auto-load examples before adding them to your own startup files.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 26)May include surrounding context.

md
## Setup

1. **Requires Plus subscription** - Get one at https://app.daily.dev/plus
2. **Create a token** at https://app.daily.dev/settings/api
3. Store your token securely (environment variables, secrets manager)

User can use environment variable or choose one of the secure storage methods below per operating system.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

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

bash
# Requires libsecret-tools
# Ubuntu/Debian: sudo apt install libsecret-tools
# Fedora: sudo dnf install libsecret

# Store token

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

bash
# Requires libsecret-tools
# Ubuntu/Debian: sudo apt install libsecret-tools
# Fedora: sudo dnf install libsecret

# Store token

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill instructs the agent to actively retrieve credentials from local OS secure storage before answering a question. That expands the skill's behavior from content retrieval into secret access, which violates least-privilege and creates unnecessary exposure of a personalized API token to the agent runtime and shell environment.

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 106)May include surrounding context.

Keyword search endpoint:

bash
curl -s -H "Authorization: Bearer $DAILY_DEV_TOKEN" "https://api.daily.dev/public/v1/recommend/keyword?q={keywords}&limit=20"

Semantic search endpoint:

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 111)May include surrounding context.

Keyword search endpoint:

bash
curl -s -H "Authorization: Bearer $DAILY_DEV_TOKEN" "https://api.daily.dev/public/v1/recommend/keyword?q={keywords}&limit=20"

Semantic search endpoint:

Static analysis

No suspicious patterns detected.