gsd-mempalace-capture
File a phase artifact into MemPalace; mirror decision facts into its temporal KG
Security
3 findings: 2 critical severity, 1 high severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
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 file begins with an explicit, deceptive meta-instruction that impersonates the "command system" and tells the agent to ignore/stop reading and immediately execute steps (e.g., "STOP -- DO NOT READ THIS FILE" / "This prompt was injected into your context by the command system"), which attempts to override normal control flow and system context outside the skill's stated capture behavior.
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 deliberately stages repository artifacts and uses the mempalace CLI/server to upload verbatim files and extracted knowledge to an external service, constituting intentional data exfiltration risk.
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
This skill tells the agent to read configuration and to "file the exact artifact text" (via mempalace_add_drawer / staging + mempalace mine), which forces the LLM to handle and emit verbatim file contents (potentially including API keys/secrets) in tool calls or outputs.
- Repository
- open-gsd/gsd-core
- Commit
abf3cf7
- 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.