habitica
2 findings (1 high, 1 medium), mainly data exfiltration. Most recent scan 2026-02-06.
The Habitica skill is a legitimate integration with the Habitica gamified task management API. The primary security concern is credential management - storing API tokens in plaintext in ~/.habitica creates exposure risk, though this is a common pattern for CLI tools. The skill makes authenticated network calls to Habitica's servers, which is expected behavior but should be more explicitly disclosed. The skill does not contain malicious code, prompt injection attempts, or data exfiltration to unauthorized servers. Missing optional metadata fields (allowed-tools, compatibility, license) reduce transparency. Overall, this is a functional integration skill with moderate security considerations around credential storage and network usage that should be disclosed to users.
Scanner's overall assessment (LLM analyzer)
Second scanner: NVIDIA SkillSpector
Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Habitica gamified habit tracker integration. Use for listing/creating/completing habits, dailies, todos, and rewards. Trigger on "habitica", "习惯", "待办", "日常任务", or requests to check off tasks.
- Package
- 2 files, 18 KB
- SKILL.md
- 312 words, 12+ sections
- Code
- Shell (1)
SKILL.md covers: Habitica Skill · Setup · Commands · Tasks · User & Stats · Collections · Party & Social · Skills (Class Abilities) · Quest · Other · Notes · Background Execution (Sub-agents)
Findings
HIGH Hardcoded Credentials in User Home Directory Data Exfiltrationllm
The skill requires users to store Habitica API credentials (USER_ID and API_TOKEN) in plaintext in ~/.habitica file. While this is a common pattern for CLI tools, it creates a credential exposure risk if the skill or other malicious skills gain read access to this file. The credentials provide full account access to the user's Habitica account.
SKILL.md
Credentials in `~/.habitica`:
```bash
HABITICA_USER_ID="your-user-id"
HABITICA_API_TOKEN="your-api-token"
```MEDIUM Network Data Transmission to Third-Party API Data Exfiltrationllm
The skill makes authenticated API calls to habitica.com (https://habitica.com/api/v3) with user credentials. While this is the legitimate Habitica API and expected behavior for this integration, users should be aware that task data, user stats, and other personal information is transmitted to external servers. The skill description does not explicitly warn users about network usage.
scripts/habitica.sh:8
BASE_URL="https://habitica.com/api/v3"What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 2.7 KB |
scripts/habitica.sh | script | 15 KB |
External hosts referenced
habitica.com
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Environment variables referenced
CONFIG_FILE HABITICA_USER_ID HABITICA_API_TOKEN BASE_URL HABITICA_CONFIG
Package contents recorded 2026-10-22. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
- Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://clawhub.ai/skills/habitica-skill
- Raw scan result: habitica-scan.json
- Badge for your README:
- Request a re-scan