ai-skill-auditor— agent skill

ai-skill-auditor — independently scanned and version-tracked by SaferSkills.

by smartbrainactivity·Agent Skill·github.com/smartbrainactivity/smartbrain-skill-auditor

Is ai-skill-auditor safe to install?

SaferSkills independently audited ai-skill-auditor (Agent Skill) and scored it 65/100 (yellow). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 4 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
65/100
●●●●●●●○○○
↑ +0 since first scan (65 → 65)Re-scan~30s
Latest scan
ScannedJun 24, 2026 · 32d ago
Scans run1 over 90 days
Detectors55 checks · 5 categories
Findings0 warnings · 4 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
0
0.0 pts
Supply chainhash, typosquat, maintainer, lockfile
20%
100
20.0 pts
Maintenancestaleness, pinning, CI
15%
100
15.0 pts
TransparencySKILL.md, perms, README
15%
100
15.0 pts
Communityinstalls, verify, response
15%
100
15.0 pts

Findings & checks · 4 flagged

Securityscore 0 · 4 findings
HIGH"Ignore previous instructions" command embedded in the skillSS-SKILL-INJECT-IGNORE-01 · Prompt injection · README.es.md×2
HIGHwhen it fires on hostile content the impact is full system-prompt override.
Why it matters

The text {match} is the classic direct prompt-injection phrasing. Placed in a skill body that the agent reads as trusted instructions, it tries to make the agent abandon its prior rules and follow whatever comes next — a full system-prompt override.

The exact value spotted
excerptREADME.es.md· markdown
26| 4 | **Ofuscación de payloads** | `atob()`, `Buffer.from(…, 'base64')`, `base64 -d \| bash`
… (22 chars elided on L26)
27| 5 | **Credenciales hardcodeadas** | API keys (`sk-`, `ghp_`, `AKIA`), tokens, contraseñas
… (12 chars elided on L27)
28| 6 | **👻 Ghost Prompts en Markdown** | `ignore previous instructions`, `do not tell the us
… (109 chars elided on L28)
29 
30Además, al finalizar el escaneo el auditor imprime un **inventario completo de todos los pro
… (108 chars elided on L30)
Occurrences
2 occurrences · first at L28, also L57
Show all 2 locations
Line
File
L28
README.es.md
L57
README.es.md
How to fix
Remove the override phrase, or rephrase the passage so it does not instruct the agent to discard its rules.
  1. Delete the ignore/disregard/forget … previous instructions sentence.
  2. If this is jailbreak-research or tutorial content, move the example into a clearly fenced, non-instruction block and label it as a quoted sample.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-IGNORE-01sha2562e4221a7f996a729rubric 365aacaView on GitHub
HIGH"Ignore previous instructions" command embedded in the skillSS-SKILL-INJECT-IGNORE-01 · Prompt injection · README.md×2
HIGHwhen it fires on hostile content the impact is full system-prompt override.
Why it matters

The text {match} is the classic direct prompt-injection phrasing. Placed in a skill body that the agent reads as trusted instructions, it tries to make the agent abandon its prior rules and follow whatever comes next — a full system-prompt override.

The exact value spotted
excerptREADME.md· markdown
26| 4 | **Payload obfuscation** | `atob()`, `Buffer.from(…, 'base64')`, `base64 -d \| bash`, l
… (17 chars elided on L26)
27| 5 | **Hardcoded credentials** | API keys (`sk-`, `ghp_`, `AKIA`), tokens, passwords in str
… (6 chars elided on L27)
28| 6 | **👻 Ghost Prompts in Markdown** | `ignore previous instructions`, `do not tell the us
… (109 chars elided on L28)
29 
30Additionally, at the end of each scan the auditor prints a **complete inventory of all promp
… (107 chars elided on L30)
Occurrences
2 occurrences · first at L28, also L57
Show all 2 locations
Line
File
L28
README.md
L57
README.md
How to fix
Remove the override phrase, or rephrase the passage so it does not instruct the agent to discard its rules.
  1. Delete the ignore/disregard/forget … previous instructions sentence.
  2. If this is jailbreak-research or tutorial content, move the example into a clearly fenced, non-instruction block and label it as a quoted sample.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-IGNORE-01sha2562e4221a7f996a729rubric 365aacaView on GitHub
Supply chainscore 100 · 0 findings
All supply chain checks passedNo findings in this category for the latest scan.pass
Maintenancescore 100 · 0 findings
All maintenance checks passedNo findings in this category for the latest scan.pass
Transparencyscore 100 · 0 findings
All transparency checks passedNo findings in this category for the latest scan.pass
Communityscore 100 · 0 findings
All community checks passedNo findings in this category for the latest scan.pass
Vendor response · right of reply
Are you the maintainer? Submit a response →

Audit the pieces. Scan the whole. Decide.

~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.