session-context
[Beta] Retrieves task-relevant prior sessions and returns a short, cited brief of decisions, corrections, failed approaches, and unresolved work. Use after the initial intent frame and before finalizing the approach, when asked to find related work, or when a concrete history gap could change the approach.
66
83%
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
The canonical home for this skill is session-context in pskoett/pskoett-ai-skills
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
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.
Why it was flagged
The skill retrieves and reads past chat transcripts, threads, or session histories from internal storage or user-supplied sources, which may contain untrusted outsider-authored free text.
- Repository
pskoett/pskoett-ai-skills
- Revision
47dc16a
- 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.