pentest-task-tree
Iterative PTT (Penetration Testing Tree) session reasoning — build, update, and traverse a live numbered task tree to drive LLM-guided pentest decisions across a full session.
61
72%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./packages/decepticon/decepticon/skills/standard/decepticon/pentest-task-tree/SKILL.mdSecurity
2 findings: 1 critical severity, 1 high severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
This skill is an offensive pentesting playbook that explicitly instructs and prioritizes credential theft, data exfiltration (downloading archives), brute-force/initial access, exploitation, and post-exploitation persistence/defense-evasion workflows—actions that enable deliberate malicious behavior or easy misuse.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill instructs the agent to "preserve all field:value pairs" when rephrasing operator notes and to emit exact commands/fields (including auth state, forms, exploit output like shell prompts or credentials), which can force the LLM to reproduce secrets verbatim in its outputs.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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
SKILL.md specifies that the agent reads the evolving session tree from `<engagement>/ptt.md` (which is written from prior tool outputs like “Web page / Burp response” text and other observed content), and those distillation inputs can include arbitrary outsider-authored web content; thus the runtime LLM context can indirectly ingest free-form text originating from external targets via the file/state and distillation pipeline.
- Repository
- PurpleAILAB/Decepticon
- Commit
e34afba
- Audited
- Security analysis
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.