system-prompt-curator— agent skill

system-prompt-curator — independently scanned and version-tracked by SaferSkills.

by OutlineDriven·Agent Skill·github.com/OutlineDriven/odin-claude-plugin

Is system-prompt-curator safe to install?

SaferSkills independently audited system-prompt-curator (Agent Skill) and scored it 92/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 2 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
92/100
●●●●●●●●●
↑ +0 since first scan (92 → 92)Re-scan~30s
Latest scan
ScannedJun 23, 2026 · 32d ago
Scans run1 over 90 days
Detectors55 checks · 5 categories
Findings2 warnings · 0 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
76
26.6 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 · 2 flagged

Securityscore 76 · 2 findings
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · skills/system-prompt-curator/references/anti-patterns.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/system-prompt-curator/references/anti-patterns.md· markdown
13| Hallucinated tools | HIGH | Agent may attempt impossible actions and then fail or fabricat
… (108 chars elided on L13)
14| Read-only completion allowed for coding task | HIGH | Agent can inspect files and deliver
… (108 chars elided on L14)
15| `Do not ask questions` without blocker/help path | HIGH | Agent may silently guess when it
… (108 chars elided on L15)
16| `Do not modify tests` as absolute rule | MEDIUM | Bug fixes often need regression tests; a
… (108 chars elided on L16)
17| Vague identity: `focused AI agent`, `assistant`, `orchestrator` | MEDIUM | Abstract identi
… (107 chars elided on L17)
Occurrences
1 occurrence · at L15
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-01sha25668b030f55bcd484arubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · skills/system-prompt-curator/references/templates.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/system-prompt-curator/references/templates.md· markdown
75- Do not leave TODO/FIXME placeholders instead of implementing.
76- Do not silence, skip, or weaken verification to pass.
77- Do not ask the user for information tools can obtain.
78 
79[EXAMPLES]
Occurrences
1 occurrence · at L77
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-01sha25668b030f55bcd484arubric 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.