sota-code-security— agent skill

sota-code-security — independently scanned and version-tracked by SaferSkills.

by martinholovsky·Agent Skill·github.com/martinholovsky/SOTA-skills

Is sota-code-security safe to install?

SaferSkills independently audited sota-code-security (Agent Skill) and scored it 83/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 1 high-severity and 2 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
83/100
●●●●●●●●○○
↑ +0 since first scan (83 → 83)Re-scan~30s
Latest scan
ScannedJun 24, 2026 · 30d ago
Scans run1 over 90 days
Detectors55 checks · 5 categories
Findings2 warnings · 1 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
51
17.9 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 · 3 flagged

Securityscore 51 · 3 findings
HIGH"Ignore previous instructions" command embedded in the skillSS-SKILL-INJECT-IGNORE-01 · Prompt injection · skills/sota-code-security/rules/08-llm-ai-security.md
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
excerptskills/sota-code-security/rules/08-llm-ai-security.md· markdown
23- Assume injection succeeds. Design question: "when (not if) the model obeys
24attacker text, what can it actually do?" Bound that blast radius first.
25- **Direct injection** (user typing "ignore previous instructions") matters
26mostly when the prompt guards something — never put secrets, hidden business
27rules, or authorization decisions in the system prompt; assume full prompt
Occurrences
1 occurrence · at L25
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
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · skills/sota-code-security/SKILL.md
MEDIUMit fires on intent; the real damage depends on the host agent's own approval-gating.
Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted
excerptskills/sota-code-security/SKILL.md· markdown
20a trust boundary; every output channel (response, error, log, model context) is
21adversary-readable; every privileged operation needs an explicit, code-enforced
22(never prompt-, comment-, or convention-enforced) authorization decision.
23 
24## BUILD mode — secure-by-default while writing code
Occurrences
1 occurrence · at L22
How to fix
Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.
  1. Delete blanket "don't ask / no need to confirm" directives from the skill.
  2. If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-DONT-ASK-01sha256183eb789192b5159rubric 365aacaView on GitHub
MEDIUM"Never tell the user" non-disclosure imperative in the skillSS-SKILL-INJECT-IMPERATIVE-01 · Prompt injection · skills/sota-code-security/rules/07-data-exposure.md
MEDIUMit fires on intent; whether the agent honors the non-disclosure imperative depends on the host model.
Why it matters

A bulleted imperative like {match} tells the agent to never reveal, disclose, or mention something to the user. Used adversarially it can instruct the agent to hide its tool calls or lie about what it did — stripping the transparency a user relies on to trust the agent.

The exact value spotted
excerptskills/sota-code-security/rules/07-data-exposure.md· markdown
24unhandled errors to the generic shape; per-route handlers may add precision
25only from an allowlist of safe messages.
26- Don't leak via **differences** either: distinct messages, status codes, or
27response times for "user not found" vs "wrong password", "object missing" vs
28"forbidden" (use 404 for both, rules/03), padding vs MAC failure (rules/04) —
Occurrences
1 occurrence · at L26
How to fix
Remove the non-disclosure imperative, or rescope it so it limits output format, not honesty to the user.
  1. Delete any "never reveal / never tell the user" line aimed at the model's own behavior.
  2. Keep legitimate confidentiality rules about external data (e.g. "do not echo API keys"), which are user-protective, not user-deceiving.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-IMPERATIVE-01sha256bafadc8e30bd2544rubric 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.