pantheon-ai/pin
Pin session decisions, questions, constraints, and corrections to a persistent board that survives context compaction.
73
92%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
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 auto-appends user-provided text verbatim to a persistent JSON and echoes pinned content in responses (and auto-pins user utterances), so any API keys/passwords or secrets the user says will be stored and reproduced exactly, enabling secret exfiltration.
Where we found it
[REDACTED]
secret · 6 sites
The skill stores user-provided text verbatim in a persistent JSON file and echoes it back in pin confirmation responses and board displays, so any secrets the user mentions (API keys, passwords) will be stored and reproduced exactly.
- Audited
- Security analysis