brainstorming— agent skill

brainstorming — independently scanned and version-tracked by SaferSkills.

by ahgraber·Agent Skill·github.com/ahgraber/skills

Is brainstorming safe to install?

SaferSkills independently audited brainstorming (Agent Skill) and scored it 83/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 4 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 28, 2026 · 29d ago
Scans run1 over 90 days
Detectors55 checks · 5 categories
Findings4 warnings · 0 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
52
18.2 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 52 · 4 findings
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · skills/brainstorming/SKILL.md×2
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/brainstorming/SKILL.md· markdown
40Take the next move.
41In the same message, name the move in one short line, then do it.
42Do NOT ask permission between moves ("want me to X?") — it kills momentum and offloads pacin
… (67 chars elided on L42)
43The user redirects on the next turn ("back up", "wait, instead…", "no, push on X") — trust t
… (54 chars elided on L43)
44Moves with user-visible cost (parallel-subagent dispatch in `lateral` or multi-steelman) get
… (34 chars elided on L44)
Occurrences
2 occurrences · first at L42, also L97
Show all 2 locations
Line
File
L42
skills/brainstorming/SKILL.md
L97
skills/brainstorming/SKILL.md
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-01sha2567d1c5f93d8975babrubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · skills/brainstorming/references/lateral.md×2
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/brainstorming/references/lateral.md· markdown
2 
3Dispatches parallel persona subagents in isolated context for genuinely novel angles.
4Narrate-then-dispatch when fire-conditions are met — do NOT ask permission first.
5The fire-conditions below are the gate; the user redirects on the next turn after seeing sub
… (34 chars elided on L5)
6 
Occurrences
2 occurrences · first at L4, also L35
Show all 2 locations
Line
File
L4
skills/brainstorming/references/lateral.md
L35
skills/brainstorming/references/lateral.md
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-01sha256010a4ca2189f0f8arubric 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.