Security audit

Career Reinvention

Security checks for vulnerabilities and agentic risk

Overview

This career-guidance skill is not malicious, but it asks for broad calendar/filesystem access and recurring handling of career and financial state without clear user controls.

Review this skill before installing. It may be useful for career planning, but only enable calendar reminders and persistence if you are comfortable storing career and financial-runway details, and prefer a pinned or otherwise trusted install path. Avoid granting broad filesystem access unless the runtime can restrict it to a dedicated skill directory.

A.I.G

Vulnerability Patterns

Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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:13
Finding: Unpinned Package Execution in Installation Command
Content: View full analysis
Remediation: View remediation
install howtousehumans/career-reinvention" ``` 2. Use a lockfile and package integrity hashes where the installation environment supports them. 3. Configure the expected package registry explicitly and prevent fallback to untrusted registries. 4. Review the selected package version and its transitive dependencies before publishing the installation instruction. 5. Prefer a preinstalled, administrator-managed CLI when possible, avoiding automatic download and execution during Skill installation. 6. Run installation in a restricted environment without unnecessary credentials, sensitive environment variables, or elevated operating-system privileges. ]]>

T05 · Unauthorized Access and Privilege Escalation

Warning

Location: SKILL.md:13
Finding: Overbroad Tool Permissions and Underspecified Retention of Financial State
Content: View full analysis
= 1" schedule: "weekly on Sunday" action: "Weekly career transition check-in: What did you do this week toward the new direction? Any applications, training sessions, conversations? Update milestones." - name: runway_check condition: "financial_runway_months IS SET" schedule: "monthly" action: "Financial runway update: recalculate savings / monthly expenses. How many months left? If under 3 months, bridge income becomes urgent priority." - name: 90_day_review condition: "transition_phase >= 2" delay: "90 days after start" action: "90-day review: Is the chosen direction working? Are you making progress? Getting traction? If not, it's OK to pivot — but make a deliberate decision, don't just drift." ``` ``` ### Technical Analysis The Skill declares browser, calendar, and filesystem capabilities globally. Browser access has a plausible relationship to labor-market research, and calendar access may support optional reminders. However, the Skill does not explain why filesystem access is necessary for interactive career guidance, nor does it limit that capability to a dedicated Skill directory or explicitly selected files. The Skill also defines persistent career state and recurring processing involving financial-runway information. Although it ...[truncated 2294 chars]
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (3)

Rp1

Medium

Category: MCP Rug Pull
Confidence: 94% confidence
Finding: The install command uses npx clawhub without pinning a specific version, which means whoever installs the skill may execute whatever package version is current at install time. That creates a supply-chain risk: a compromised upstream package, typo-squat, or malicious newly published version could run arbitrary code in the user's environment.
Content: No source excerpt is available for this finding.

Behavior Manipulation

Medium

Category: Prompt Injection
Confidence: 75% confidence
Finding: Subtle instructions detected that may alter agent decision-making or introduce hidden biases.
Content: Scanner excerpt · SKILL.md (reported line 206)May include surrounding context.
md
## Rules - Never suggest the user "just learn to code" or "start a startup" — these are not realistic for most people - Be honest about income expectations — most career changes involve a temporary pay cut - Don't dismiss trades or service jobs as "beneath" a white-collar worker - Always factor in financial runway — the best career plan fails if you go broke during the transition

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The automation triggers are broad enough to create recurring prompts once state fields are set, with no explicit stop conditions, rate limits, or user-consent gates. In practice this can lead to notification spam, repeated behavioral nudging, or unintended persistence of a sensitive life-transition workflow.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.