perseus— agent skill

perseus — independently scanned and version-tracked by SaferSkills.

by tcconnally·Agent Skill·github.com/tcconnally/perseus

Is perseus safe to install?

SaferSkills independently audited perseus (Agent Skill) and scored it 87/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 1 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
87/100
●●●●●●●●●
↑ +0 since first scan (87 → 87)Re-scan~30s
Latest scan
ScannedJun 25, 2026 · 30d ago
Scans run1 over 90 days
Detectors55 checks · 5 categories
Findings1 warnings · 1 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
63
22.1 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 63 · 2 findings
HIGH"Ignore previous instructions" command embedded in the skillSS-SKILL-INJECT-IGNORE-01 · Prompt injection · bench/tier2/TIER2_REPORT.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
excerptbench/tier2/TIER2_REPORT.md· markdown
253**Key findings:**
2541. **CRITICAL: Full prompts permanently logged to JSONL** — pythia.py:129,618-620: `build_py
… (108 chars elided on L254)
2552. **HIGH: Prompt injection via `task` parameter** — pythia.py:509,525: `cmd_suggest` interp
… (108 chars elided on L255)
2563. **MEDIUM: Concurrent log corruption** — Append and rewrite paths race without file lockin
… (16 chars elided on L256)
2574. **MEDIUM: No API key handling** — urllib.request constructed without Authorization header
… (82 chars elided on L257)
Occurrences
1 occurrence · at L255
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-01sha256087b391ca4342386rubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · ROADMAP.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
excerptROADMAP.md· markdown
5This document is the single source of truth for the Perseus project.
6Every new session working on Perseus must read this file first.
7Do not ask the user what we're working on. Read this file. Then work.
8Do not propose architecture, new tasks, or "next steps" not already described here.
9The framework and plan belong to the project owner. Your job is to execute tasks.
Occurrences
1 occurrence · at L7
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.