T09 · Insecure Skill Coding Practices
Warning
- Location
references/artifact-recipes.md:16- Finding
Unredacted HAR Collection May Expose Authentication Secrets and Private Data
- Content
View full analysis
- Remediation
View remediation
Security audit
god-of-slop
Security checks for vulnerabilities and agentic risk
Overview
This is a quality-control skill, but it needs review because it can ask users to upload broad debugging artifacts such as full HAR files without privacy or redaction warnings.
Install only if you are comfortable with the agent asking for diagnostic artifacts. Before sharing HAR files, console logs, screenshots, recordings, documents, audio, or file paths, review and redact cookies, authorization headers, tokens, account identifiers, internal URLs, and confidential content; prefer screenshots or selected request details before full exports.
Vulnerability Patterns
- 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
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)
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)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The opt-out trigger includes the phrase "just write it," which is broad, colloquial language that can easily appear in normal user requests unrelated to disabling safeguards. An attacker or even an ordinary user could unintentionally suppress the pre-flight safety behavior, causing the skill to skip checks for missing inputs, modality gaps, or unverifiable assumptions and increasing the chance of unsafe or low-integrity outputs.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The guidance tells users to export and send HAR files, console output, file paths, and arbitrary documents without any warning that these artifacts can contain sensitive data such as cookies, authorization headers, personal documents, local usernames, or internal URLs. In a skill specifically designed to collect debugging artifacts quickly, this omission increases the chance that users will overshare sensitive information to the agent or service handling the chat.
- Content
Static analysis
No suspicious patterns detected.