T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:52- Finding
Sensitive Personal Diary Data Stored in Plaintext
- Content
View full analysis
- Remediation
View remediation
Security audit
Dear Agent: AI Diary and Journal Keeper
Security checks for vulnerabilities and agentic risk
Overview
This diary skill is not malicious, but it can persist sensitive personal memories from ordinary conversation with limited consent controls.
Review before installing if you do not want an agent to proactively save personal conversations, photos, voice notes, moods, and relationship details into a persistent local diary. Prefer using it only with explicit save commands or after confirmation for sensitive entries, and protect the local DEAR_AGENT_DIR because entries are stored as plaintext markdown.
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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)
Vague Triggers
High
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The activation description is extremely broad and includes vague triggers like 'any moment the user is clearly recording their life,' which can cause the skill to activate during ordinary personal conversation without sufficiently explicit consent. In a diary skill handling highly sensitive personal data, overbroad activation materially increases the risk of silently storing intimate information the user did not intend to memorialize.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The proactive capture guidance instructs the agent to infer when to save diary entries from routine statements about meetings, feelings, milestones, photos, and voice notes. That ambiguity can lead to over-collection of private data and creation of persistent records from casual conversation, especially because the skill is framed as 'quietly' keeping the diary in the background.
- Content