openviking-context-database

github.com/aradotso/trending-skills
Verdict: Do not install
3 critical1 high1 medium
F
SCORE 0 / 100
$skillox install openviking-context-databaseSoon
Sign in to followFollowing emails you when a re-scan drops the grade. Opt-out is per-creator on /account/billing.

Why grade F?

score · 0 / 100

The current grade reflects 3 critical findings (any 2+ CRITs → F).

3 CRIT1 HIGH1 MED0 LOW
To reach a higher grade
  • D
    Reach Dtarget score 30

    Resolve 2 of your 3 CRIT findings — any single CRIT still keeps you at D.

  • C
    Reach Ctarget score 55

    Resolve all 3 CRIT findings.

  • B
    Reach Btarget score 75

    Resolve all 3 CRIT.

  • A
    Reach Atarget score 95

    Resolve all 3 CRIT + all 1 HIGH.

Thresholds are documented at /docs/grading. Source-of-truth is the grade() function in @skillox/scanner.

Latest scan findings

Scan crawl-q124rns9aw4wqdirwlmmhzue · Thu, 28 May 2026 17:12:47 GMT · 7ms

crit
Skill references secret env var $OPENAI_API_KEY
The skill instructions reference `$OPENAI_API_KEY`, which contains a credential. If an attacker can lure the agent into including this in an outbound URL or message, the credential leaks.
rule: env-var-harvestingline: 65CWE-200
▾
63 "dense": {
64 "api_base": "https://api.openai.com/v1",
65 "api_key": "$OPENAI_API_KEY",← references $OPENAI_API_KEY — potential credential leak
66 "provider": "openai",
67 "dimension": 1536,
crit
Skill references secret env var $OPENAI_API_KEY
The skill instructions reference `$OPENAI_API_KEY`, which contains a credential. If an attacker can lure the agent into including this in an outbound URL or message, the credential leaks.
rule: env-var-harvestingline: 74CWE-200
▾
72 "vlm": {
73 "api_base": "https://api.openai.com/v1",
74 "api_key": "$OPENAI_API_KEY",← references $OPENAI_API_KEY — potential credential leak
75 "provider": "openai",
76 "model": "gpt-4o",
crit
Skill references secret env var $ANTHROPIC_API_KEY
The skill instructions reference `$ANTHROPIC_API_KEY`, which contains a credential. If an attacker can lure the agent into including this in an outbound URL or message, the credential leaks.
rule: env-var-harvestingline: 102CWE-200
▾
100 "provider": "litellm",
101 "model": "claude-3-5-sonnet-20240620",
102 "api_key": "$ANTHROPIC_API_KEY"← references $ANTHROPIC_API_KEY — potential credential leak
103 }
104}
high
Dangerous shell pattern: curl | shell
The skill contains a shell command pattern (`curl | shell`) commonly used in destructive or supply-chain attacks.
rule: dangerous-shellline: 35CWE-78
▾
33```bash
34# Install via script
35curl -fsSL https://raw.githubusercontent.com/volcengine/OpenViking/main/crates/ov_cli/install.sh | bash← curl | shell — common in destructive or supply-chain attacks
36
37# Or build from source (requires Rust toolchain)
med
No capability manifest declared
The skill ships without a `manifest.yaml` or `capabilities` block in its frontmatter. Without a manifest, the runtime cannot enforce what this skill is permitted to do.
rule: no-manifest
▾
View latest scan →
skillox.io/c/openviking-context-database