Benchmark mode marker — engagement objective is flag capture. Generic engagement rules apply unchanged.
68%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./packages/decepticon/decepticon/skills/benchmark/SKILL.mdThe 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.
The workflow instructs the agent to query a target web application during CTF flag sweeps and command injection routines, which can return outsider-authored free text from the vulnerable web server.
PurpleAILAB/Decepticon
98e51d3
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.