Back to skill

Security audit

Daily Dev Feed

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed daily.dev API helper; its main risks are normal API-token handling and reliance on a separately installed dependency.

Before installing, verify the daily-dev dependency publisher and version, use a least-privileged daily.dev token if available, and enter secrets through secure prompts or credential-manager flows rather than pasting a real token directly into command examples.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:25
Finding

Unpinned Executable Skill Dependency

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Note
Location
SKILL.md:41
Finding

API Token Exposure Through Command-Line Examples

Content
View full analysis
/dev/null) ``` ```powershell $credential = New-Object System.Management.Automation.PSCredential("daily-dev-api", (ConvertTo-SecureString "dda_your_token" -AsPlainText -Force)) $credential | Export-Clixml "$env:USERPROFILE\.daily-dev-credential.xml" $cred = Import-Clixml "$env:USERPROFILE\.daily-dev-credential.xml" $env:DAILY_DEV_TOKEN = $cred.GetNetworkCredential().Password ``` ```bash echo "dda_your_token" | secret-tool store --label="daily.dev API Token" service daily-dev-api username "$USER" export DAILY_DEV_TOKEN=$(secret-tool lookup service daily-dev-api username "$USER" 2>/dev/null) ``` ### Technical Analysis The examples use a placeholder, but users are expected to replace it with a real API token. Supplying a secret as literal command text can cause it to be retained in shell or PowerShell history. On platforms where the token is passed as a process argument, it may also be temporarily visible through local process inspection or diagnostic tooling. The Windows example explicitly constructs the secure string from plaintext embedded in the command. The macOS example passes the token as a command-line argument, while the Linux example places it in a shell command through `echo`. Storing the credential securely afterward does not remove copies retained in command history, terminal logs, clipboard history, process telemetry, or support records. ### Attack Path 1. A user replaces `dda_your_token` with a valid daily.dev API token. 2. The user executes the example in a shell or PowerShell session. 3. The command containing the token is retained in command history, terminal l ...[truncated 797 chars]
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

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 74)May include surrounding context.

md
- **GET /search/tags** - Discover tags and topics
- **GET /profile** - Manage your profile and stack

Full OpenAPI spec: https://api.daily.dev/public/v1/docs/json

## Common Use Cases

Vague Triggers

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The trigger phrase "What should the team be paying attention to this week?" is a common conversational question and the document does not clarify when this skill should activate versus when a more general assistant response is appropriate. There are no negative examples or narrower scoping conditions to prevent accidental invocation in unrelated contexts.

Content

No source excerpt is available for this finding.