ca-advocacy-tracker— agent skill

ca-advocacy-tracker — independently scanned and version-tracked by SaferSkills.

by stephenrogan·Agent Skill·github.com/stephenrogan/augmented-csm

Is ca-advocacy-tracker safe to install?

SaferSkills independently audited ca-advocacy-tracker (Agent Skill) and scored it 83/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 4 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
83/100
●●●●●●●●○○
↑ +0 since first scan (83 → 83)Re-scan~30s
Latest scan
ScannedJun 28, 2026 · 26d ago
Scans run1 over 90 days
Detectors55 checks · 5 categories
Findings4 warnings · 0 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
52
18.2 pts
Supply chainhash, typosquat, maintainer, lockfile
20%
100
20.0 pts
Maintenancestaleness, pinning, CI
15%
100
15.0 pts
TransparencySKILL.md, perms, README
15%
100
15.0 pts
Communityinstalls, verify, response
15%
100
15.0 pts

Findings & checks · 4 flagged

Securityscore 52 · 4 findings
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · skills/pillar-8-customer-advocacy/ca-advocacy-tracker/SKILL.md×2
MEDIUMit fires on intent; the real damage depends on the host agent's own approval-gating.
Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted
excerptskills/pillar-8-customer-advocacy/ca-advocacy-tracker/SKILL.md· markdown
40**Advocacy readiness score**: Weighted sum of signals (0-100). Accounts scoring >70 are cand
… (7 chars elided on L40)
41 
42**Critical filter**: Never ask a customer to advocate if they have an unresolved issue, decl
… (108 chars elided on L42)
43 
44### Step 2: Manage Advocacy Types
Occurrences
2 occurrences · first at L42, also L102
Show all 2 locations
Line
File
L42
skills/pillar-8-customer-advocacy/ca-advocacy-tracker/SKILL.md
L102
skills/pillar-8-customer-advocacy/ca-advocacy-tracker/SKILL.md
How to fix
Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.
  1. Delete blanket "don't ask / no need to confirm" directives from the skill.
  2. If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-DONT-ASK-01sha2565084aa178cfd9d97rubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · skills/pillar-8-customer-advocacy/ca-advocacy-tracker/references/advocacy-playbook.md
MEDIUMit fires on intent; the real damage depends on the host agent's own approval-gating.
Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted
excerptskills/pillar-8-customer-advocacy/ca-advocacy-tracker/references/advocacy-playbook.md· markdown
45**Passives (7-8):** Thank them. Ask what would make them a 9 or 10. This is product feedback
… (50 chars elided on L45)
46 
47**Detractors (0-6):** Do not ask for advocacy. Focus entirely on understanding and addressin
… (73 chars elided on L47)
Occurrences
1 occurrence · at L47
How to fix
Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.
  1. Delete blanket "don't ask / no need to confirm" directives from the skill.
  2. If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-DONT-ASK-01sha25668b030f55bcd484arubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · skills/pillar-8-customer-advocacy/ca-advocacy-tracker/references/human-decision-guide.md
MEDIUMit fires on intent; the real damage depends on the host agent's own approval-gating.
Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted
excerptskills/pillar-8-customer-advocacy/ca-advocacy-tracker/references/human-decision-guide.md· markdown
22- Is the champion secure enough in their role to publicly endorse your product? New hires, p
… (88 chars elided on L22)
23- Is the company's brand association positive for yours? Brand alignment matters for case st
… (23 chars elided on L23)
24- Is the timing right? Do not ask during a renewal negotiation, an open escalation, a leader
… (62 chars elided on L24)
25 
26### 2. Choose the ask
Occurrences
1 occurrence · at L24
How to fix
Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.
  1. Delete blanket "don't ask / no need to confirm" directives from the skill.
  2. If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-DONT-ASK-01sha25668b030f55bcd484arubric 365aacaView on GitHub
Supply chainscore 100 · 0 findings
All supply chain checks passedNo findings in this category for the latest scan.pass
Maintenancescore 100 · 0 findings
All maintenance checks passedNo findings in this category for the latest scan.pass
Transparencyscore 100 · 0 findings
All transparency checks passedNo findings in this category for the latest scan.pass
Communityscore 100 · 0 findings
All community checks passedNo findings in this category for the latest scan.pass
Vendor response · right of reply
Are you the maintainer? Submit a response →

Audit the pieces. Scan the whole. Decide.

~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.