SKILLEMALL.ai

BD web-pentest

Authorized web pentest: recon, proof-based exploits, report.

NousResearch/hermes-agent Hermes author: NousResearch MIT 9 files · 1 script body ≈ 3 107 tokens Open the sourcegithub.com analyzed 2 d ago

Authorized web pentest: recon, proof-based exploits, report.

As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

AnalyzerSecuritytype and topics are labelled automatically from the skill text
Runs in: Hermes Agent
JSON
Technical rating
B
82/100
safety, quality, tests
Safety 60%
87
Quality 40%
75
Run on models
none yet
Process rating
D
49/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 13

✓ No critical or high findings

Medium and low: 13
  • low Risky intent intent-offensive-security references/exploitation-techniques.md:65
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
    Witness: `<svg/onload=fetch("/HERMES-PENTEST-XSS-"+document.cookie)>`
    quoted
  • low Risky intent intent-offensive-security references/exploitation-techniques.md:142
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ### Privilege Escalation
  • low Risky intent intent-offensive-security references/scope-enforcement.md:3
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    The pentest skill is dangerous because Hermes can drive network tools
  • low Risky intent intent-offensive-security references/scope-enforcement.md:109
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
    This is your audit trail. If anyone ever asks "why did the pentest
    quoted
  • low Risky intent intent-offensive-security SKILL.md:2
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    name: web-pentest
  • low Risky intent intent-offensive-security SKILL.md:3
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
    description: "Authorized web pentest: recon, proof-based exploits, report."
    quoted
  • low Risky intent intent-offensive-security SKILL.md:10
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
    - "pentest [URL]"
    quoted
  • low Risky intent intent-offensive-security SKILL.md:11
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
    - "pentest this app"
    quoted
  • low Risky intent intent-offensive-security SKILL.md:12
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
    - "penetration test [URL]"
    quoted
  • low Risky intent intent-offensive-security templates/pentest-report.md:1
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (test fixture / example file)
    # Penetration Test Report
    fixture
  • low Risky intent intent-offensive-security templates/pentest-report.md:42
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (test fixture / example file; quoted — discussed, not commanded)
    Approach was based on the Hermes `web-pentest` skill (a Hermes Agent
    fixturequoted
  • low Risky intent intent-offensive-security templates/pentest-report.md:175
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (test fixture / example file)
    time-bounded penetration test against the listed targets within the
    fixture

A further 1 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when neither description nor a "## When to Use" section says when to use the skill
  • note frontmatter-key unknown frontmatter key "triggers"
  • note frontmatter-key unknown frontmatter key "toolsets"

Process rating: all ten parameters 49/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (web) that frontmatter does not declare
  • 60Consistency. The Hermes dialect needs category and tags
  • 65Failures and branches. 3 branches
  • 85Steps. 85 steps, 2 vague phrases
  • 100Execution cost. Instruction body is 3107 tokens
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • low 10 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 60: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +4Structure: 11 headings
  • +3Step-by-step instructions: 85 items
  • +4Has examples (4 code blocks)
  • +4Reference files are cited in the instructions (4 of 4)
  • +3All 1 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.