pantheon-ai/retrospect-domain
Extract domain insights, patterns, and learnings from captured sessions for long-term knowledge retention.
63
79%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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 required runtime workflow loads and reads “captured sessions” via `retrospect-load-sessions.sh` and then “Read session files — extract conversation turns,” which can include free-form text authored by other parties (e.g., collaborators/other users) that the operating user did not choose to introduce into the LLM context.
- Audited
- Security analysis