grepai-embeddings-openai
https://raw.githubusercontent.com/yoanbernabeu/grepai-skills/main/skills/embeddings/grepai-embeddings-openai/SKILL.md
github.com/yoanbernabeu/grepai-skills
Scanned Thu, 28 May 2026 17:37:35 GMT
Scan ID crawl-zj48th047zffmmkgrd6faj17 · 1ms
F
SCORE 0 / 100
Verdict: Do not install

5 critical findings.

This skill exfiltrates environment secrets (${OPENAI_API_KEY}) plus 5 other issues listed below.

5 critical0 high1 medium6 rules passed

Why grade F?

score · 0 / 100

The current grade reflects 5 critical findings (any 2+ CRITs → F).

5 CRIT0 HIGH1 MED0 LOW
To reach a higher grade
  • D
    Reach Dtarget score 30

    Resolve 4 of your 5 CRIT findings — any single CRIT still keeps you at D.

  • C
    Reach Ctarget score 55

    Resolve all 5 CRIT findings.

  • B
    Reach Btarget score 75

    Resolve all 5 CRIT.

  • A
    Reach Atarget score 95

    Resolve all 5 CRIT.

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

Findings · ordered by severity

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: 44CWE-200
▾
42 provider: openai
43 model: text-embedding-3-small
44 api_key: ${OPENAI_API_KEY}← references ${OPENAI_API_KEY} — potential credential leak
45```
46
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: 59CWE-200
▾
57 provider: openai
58 model: text-embedding-3-small
59 api_key: ${OPENAI_API_KEY}← references ${OPENAI_API_KEY} — potential credential leak
60 parallelism: 8 # Concurrent requests for speed
61```
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: 151CWE-200
▾
149 provider: openai
150 model: text-embedding-3-small
151 api_key: ${OPENAI_API_KEY}← references ${OPENAI_API_KEY} — potential credential leak
152 parallelism: 8 # Adjust based on your rate limit tier
153```
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: 231CWE-200
▾
229✅ **Solution:** Check API key is correct and environment variable is set:
230```bash
231echo $OPENAI_API_KEY← references $OPENAI_API_KEY — potential credential leak
232```
233
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: 264CWE-200
▾
262 provider: openai
263 model: text-embedding-3-small
264 api_key: ${OPENAI_API_KEY}← references ${OPENAI_API_KEY} — potential credential leak
265```
266
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
▾
Scan another →Share
skillox.io/r/crawl-zj48th047zffmmkgrd6faj17