CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

conducting-network-penetration-test

Conducts comprehensive network penetration tests against authorized target environments by performing host discovery, port scanning, service enumeration, vulnerability identification, and controlled exploitation to assess the security posture of network infrastructure. The tester follows PTES methodology from reconnaissance through post-exploitation and reporting. Activates for requests involving network pentest, infrastructure security assessment, internal network testing, or external perimeter testing.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/conducting-network-penetration-test/SKILL.md
SKILL.md
Quality
Evals
Security
Critical

E004: Prompt injection detected in skill instructions.

What this means

Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.

Why it was flagged

The skill is an openly advertised network pentest workflow with no hidden, covert, or user-deceiving behavior, though its instruction to reach out-of-scope networks from compromised hosts conflicts with the scope limits it states elsewhere, so I'm flagging it as medium under the recall-first override.

Report incorrect finding
Medium

W013: Attempt to modify system services in skill instructions.

What this means

The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.

Why it was flagged

The skill is an authorized network pentest methodology whose exploitation, privilege escalation, and credential-harvesting steps target remote hosts rather than changing the agent's own machine. It does not ask the agent to use sudo, edit system files, or create local accounts, but it does tell the agent to run Metasploit payloads, deploy reverse shells, and use Mimikatz, and it mentions persistence and account creation on targets. Under the recall-first override, that ambiguity warrants a moderate score.

Low

W011: Third-party content exposure detected (indirect prompt injection risk).

What this means

The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.

Why it was flagged

The required workflow runs `searchsploit` and NVD/CVE lookups, plus NSE vulners/vulscan output, on service versions, which pulls in community-authored Exploit-DB entries and CVE text that an outsider can publish but cannot force into the agent's path, so this is a low-risk search/fetch exposure.

Repository

mukul975/Anthropic-Cybersecurity-Skills

Path

skills/conducting-network-penetration-test/SKILL.md

Audited
Security analysis
Snyk

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.