Use for reverse engineering stripped Go and Rust binaries including runtime recognition, pclntab/moduel data recovery, panic strings, and idiomatic decompilation recovery.
84%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
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.
The skill is a legitimate Go/Rust reverse-engineering guide, but its "NOW" step directs the agent to read an unseen external journal file before acting, which is an unexplained instruction source that could hide directives, so I rate it medium under the recall-first override.
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.
The required workflow extracts strings and symbol names from a user-selected, potentially attacker-authored binary sample (via `extract_strings.py` and `pe_exports.py`), which is low-risk because the agent must actively choose the sample and the attacker cannot force delivery into a monitored queue.
zhaoxuya520/reverse-skill
b972ad0
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.