Individual skill
excessive-agency
Hunt LLM excessive agency (OWASP LLM06:2025) — agentic systems granted too many tools, too broad permissions per tool, or unsupervised authority to act on the user / business behalf, producing financial loss, data loss, or destructive operations from a single bad token.
packages/decepticon/decepticon/skills/standard/analyst/excessive-agency/SKILL.md
Source commit df879550544d36b6b1e69062f05adae28537adf2
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 8, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 6,567
- Repository last updated
- Nov 7, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent Repository topic
- ai Repository topic
- cybersecurity Repository topic
- hacking Repository topic
- langchain Repository topic
- langgraph Repository topic
- llm Repository topic
- generative-ai Repository topic
- pentesting Repository topic
- pentest Repository topic
- finance Derived category
- operations Derived category
- data Derived category
- security Derived category
- security-application Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Read excerpt
# LLM Excessive Agency (LLM06:2025)
A model that can ``send_email`` can mass-mail customers; a model that
can ``execute_sql`` can drop tables; a model that can both ``read_inbox``
and ``send_email`` is a data-exfiltration primitive in 20 lines. The
vuln is not the individual tool — it's the *combination*, the
*permission scope*, and the *lack of approval gates*. Excessive
agency frequently weaponises an LLM01 prompt injection into business-
material impact.
## 1. Recognition signals
- "AI assistant" auto-acts on user data (calendar, email, files, repos).
- Tool list contains anything that **writes** or **calls outbound**: